RecSys 2015 - Accepted Contributions - RecSys – RecSys

JavaScript seems to be Disabled! Some of the website features are unavailable unless JavaScript is enabled.

Accepted Contributions

List of all papers accepted for RecSys 2015 (in alphabetical order).

No matches were found!

A Probabilistic Model for Using Social Networks in Personalized Item Recommendation
by Allison J.B. Chaney, David M. Blei and Tinpa Eliassi-Rad

Preference-based recommendation systems have transformed how we consume media. By analyzing usage data, these methods uncover our latent preferences for items (such as articles or movies) and form recommendations based on the behavior of others with similar tastes. But traditional preference-based recommendations do not account for the social aspect of consumption, where a trusted friend might point us to an interesting item that does not match our typical preferences. In this work, we aim to bridge the gap between preference- and social-based recommendations. We develop social Poisson factorization (SPF), a probabilistic model that incorporates social network information into a traditional factorization method; SPF introduces the social aspect to algorithmic recommendation. We develop a scalable algorithm for analyzing data with SPF, and demonstrate that it outperforms competing methods on six real-world datasets; data sources include a social reader and Etsy.

Session 1b: Recommender Systems and Social Networks

Adaptation and Evaluation of Recommendations for Short-term Shopping Goals
by Dietmar Jannach, Lukas Lerche and Michael Jugovac

An essential characteristic in many of e-commerce settings is that website visitors can have very specific short-term shopping goals when they browse the site. Relying solely on long-term user models that are pre-trained on historical data can therefore be insufficient for recommendation. Simple “real-time” recommendation approaches based, e.g., on unpersonalized co-occurrence patterns, on the other hand do not fully exploit the available information about the user’s long-term preference profile.

In this work, we aim to explore and quantify the effectiveness of using and combining long-term models and short-term adaptation strategies. We conducted an empirical evaluation based on a novel evaluation design and two real-world datasets. The results indicate that maintaining short-term content-based and recency-based profiles of the visitors can lead to significant accuracy increases. At the same time, the experiments show that the choice of the algorithm for learning the long term preferences is particularly important at the beginning of new shopping sessions.

Session 5b: E-commerce & Ads

Applying Differential Privacy to Matrix Factorization
by Arnaud Berlioz, Arik Friedman, Mohamed Ali Kafaar, Roksana Boreli and Shlomo Berkovsky

Recommender systems are increasingly becoming an integral part of on-line services. As the recommendations rely on personal user information, there is an inherent loss of privacy resulting from the use of such systems. While several works studied privacy-enhanced neighborhood-based recommendations, little attention has been paid to privacy preserving latent factor models, like those represented by matrix factorization techniques. In this paper, we address the problem of privacy preserving matrix factorization by utilizing differential privacy, a rigorous and provable privacy preserving method. We propose and study several approaches for applying differential privacy to matrix factorization, and evaluate the privacy-accuracy trade-offs offered by each approach. We show that input perturbation yields the best recommendation accuracy, while guaranteeing a solid level of privacy protection.

Session 3: Distinguished Papers

Beyond ‘Hitting the Hits’ – Generating Coherent Music Playlist Continuations with the Right Tracks
by Dietmar Jannach, Lukas Lerche and Iman Kamehkhosh

Automated playlist generation is a special form of music recommendation and a common feature of digital music playing applications. A particular challenge of the task is that the recommended items should not only match the general listener’s preference but should also be coherent with the most recently played tracks. In this work, we propose a novel algorithmic approach and optimization scheme to generate playlist continuations that address these requirements. In our approach, we first use collections of shared music playlists, music metadata, and user preferences to select suitable tracks with high accuracy. Next, we apply a generic re-ranking optimization scheme to generate playlist continuations that match the characteristics of the last played tracks. An empirical evaluation on three collections of shared playlists shows that the combination of different input signals helps us to achieve high accuracy during track selection and that the re-ranking technique can both help to balance different quality optimization goals and to further increase accuracy.

Session 5a: News and Media

Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks
by Fabian Christoffel, Bibek Paudel, Chris Newell and Abraham Bernstein

User satisfaction is often dependent on providing accurate and diverse recommendations. In this paper, we explore scalable algorithms that exploit random walks as a sampling technique to obtain diverse recommendations without compromising on accuracy. Specifically, we present a novel graph vertex ranking recommendation algorithm called RP3beta that re-ranks items based on 3-hop random walk transition probabilities. We show empirically, that RP3beta provides accurate recommendations with high long-tail item frequency at the top of the recommendation list. We also present scalable approximate versions of RP3beta and the two most accurate previously published vertex ranking algorithms based on random walk transition probabilities and show that these approximations converge with increasing number of samples.

Session 4b: Algorithms

Cold-Start Item and User Recommendation with Decoupled Completion and Transduction
by Iman Barjasteh, Rana Forsati, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

A major challenge in collaborative filtering based recommender systems is how to provide recommendations when rating data is sparse or entirely missing for a subset of users or items, commonly known as the cold-start problem. In recent years, there has been considerable interest in developing new solutions that address the cold-start problem. These solutions are mainly based on the idea of exploiting other sources of information to compensate for the lack of rating data. In this paper, we propose a novel algorithmic framework based on matrix factorization that simultaneously exploits the similarity information among users and items to alleviate the cold-start problem. In contrast to existing methods, the proposed algorithm decouples the following two aspects of the cold-start problem: (a) the completion of a rating sub-matrix, which is generated by excluding cold-start users and items from the original rating matrix; and (b) the transduction of knowledge from existing ratings to cold-start items/users using side information. This crucial difference significantly boosts the performance when appropriate side information is incorporated. We provide theoretical guarantees on the estimation error of the proposed two-stage algorithm based on the richness of similarity information in capturing the rating data. To the best of our knowledge, this is the first algorithm that addresses the cold-start problem with provable guarantees. We also conduct thorough experiments on synthetic and real datasets that demonstrate the effectiveness of the proposed algorithm and highlights the usefulness of auxiliary information in dealing with both cold-start users and items.

Session 2b: Cold Start and Hybrid Recommender Systems

Content Driven User Profiling for Comment-Worthy Recommendations of News and Blog Articles
by Trapit Bansal, Mrinal Das and Chiranjib Bhattacharyya

We consider the problem of recommending comment-worthy articles such as news and blog-posts. An article is defined to be comment-worthy for a particular user if that user is interested to leave a comment on it. We note that recommending comment-worthy articles calls for elicitation of commenting-interests of the user from the content of both the articles and the past comments made by users. We thus propose to develop content-driven user profiles to elicit these latent interests of users in commenting and use them to recommend articles for future commenting. The difficulty of modeling comment content and the varied nature of users’ commenting interests make the problem technically challenging.

The problem of recommending comment-worthy articles is resolved by leveraging article and comment content through topic modeling and the co-commenting pattern of users through collaborative filtering, combined within a novel hierarchical Bayesian modeling approach. Our solution, Collaborative Correspondence Topic Models (CCTM), generates user profiles which are leveraged to provide a personalized ranking of comment-worthy articles for each user. Through these content-driven user profiles, CCTM effectively handle the ubiquitous problem of cold-start without relying on additional meta-data. The inference problem for the model is intractable with no off-the-shelf solution and we develop an efficient Monte Carlo EM algorithm. CCTM is evaluated on three real world data-sets, crawled from two blogs, ArsTechnica (AT) Gadgets (102,087 comments) and AT-Science (71,640 comments), and a news site, DailyMail (33,500 comments). We show average improvement of 14% (warm-start) and 18% (cold-start) in AUC, and 80% (warm-start) and 250% (cold-start) in Hit-Rank@5, over state of the art.

Session 5a: News and Media

Context-Aware Event Recommendation in Event-based Social Networks
by Augusto Q. Macedo, Leandro B. Marinho and Rodrygo L. T. Santos

The Web has grown into one of the most important channels to communicate social events nowadays. However, the sheer volume of events available in event-based social networks (EBSNs) often undermines the users’ ability to choose the events that best fit their interests. Recommender systems appear as a natural solution for this problem, but differently from classic recommendation scenarios (e.g. movies, books), the event recommendation problem is intrinsically cold-start. Indeed, events published in EBSNs are typically short-lived and, by definition, are always in the future, having little or no trace of historical attendance. To overcome this limitation, we propose to exploit several contextual signals available from EBSNs. In particular, besides content-based signals based on the events’ description and collaborative signals derived from users’ RSVPs, we exploit social signals based on group memberships, location signals based on the users’ geographical preferences, and temporal signals derived from the users’ time preferences. Moreover, we combine the proposed signals for learning to rank events for personalized recommendation. Thorough experiments using a large crawl of Meetup.com demonstrate the effectiveness of our proposed contextual learning approach in contrast to state-of-the-art event recommenders from the literature.

Session 3: Distinguished Papers

Dynamic Poisson Factorization
by Laurent Charlin, Rajesh Ranganath, James McInerney and David M. Blei

Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items (e.g., movies, books, academic papers). Typically, the latent factors are assumed to be static and, given these factors, the observed preferences and behaviors of users are assumed to be generated without order. These assumptions limit the explorative and predictive capabilities of such models, since users’ interests and item popularity may evolve over time. To address this, we propose dPF, a dynamic matrix factorization model based on the recent Poisson factorization model for recommendations. dPF models the time evolving latent factors with a Kalman filter and the actions with Poisson distributions. We derive a scalable variational inference algorithm to infer the latent factors. Finally, we demonstrate dPF on 10 years of user click data from arXiv.org, one of the largest repository of scientific papers and a formidable source of information about the behavior of scientists. Empirically we show performance improvement over both static and, more recently proposed, dynamic recommendation models. We also provide a thorough exploration of the inferred posteriors over the latent variables.

Session 4b: Algorithms

E-commerce Recommendation with Personalized Promotion
by Qi Zhao, Yi Zhang, Daniel Friedman and Fangfang Tan

Most existing e-commerce recommender systems aim to recommend the right products to a consumer, assuming the properties of each product are fixed. However, some properties, including price discount, can be personalized to respond to each consumer’s preference. This paper studies how to automatically set the price discount when recommending a product, in light of the fact that the price often will alter a consumer’s purchase decision. The key to optimizing the discount is to predict consumer’s willingness-to-pay (WTP), namely, the highest price a consumer is willing to pay for a product. Purchase data used by traditional e-commerce recommender systems provide points below or above the decision boundary. In this paper we collected training data to better predict the decision boundary. We implement a new e-commerce mechanism adapted from laboratory lottery and auction experiments that elicit a rational customer’s exact WTP for a small subset of products, and use a machine learning algorithm to predict the customer’s WTP for other products. The mechanism is implemented on our own e-commerce website that leverages Amazon’s data and subjects recruited via Mechanical Turk. The experimental results demonstrate that the proposed approach can better predict WTP, dramatically improve conversion rate and sales revenue.

Session 5b: E-commerce & Ads

ExcUseMe: Asking Users to Help in Item Cold-Start Recommendations
by Michal Aharon, Oren Anava, Noa Avigdor-Elgrabli, Dana Drachsler-Cohen, Shahar Golan, and Oren Somekh

The item cold-start problem is of a great importance in collaborative filtering (CF) recommendation systems. It arises when new items are added to the inventory and the system cannot model them properly since it relies solely on historical users’ interactions (e.g., ratings). Much work has been devoted to mitigate this problem mostly by employing hybrid approaches that combine content-based recommendation techniques or by devoting a portion of the user traffic for exploration to gather interactions from random users.

We focus on pure CF recommender systems (i.e., without content or context information) in a realistic online setting, where random exploration is inefficient and smart exploration that carefully selects users is crucial due to the huge flux of new items with short lifespan. We further assume that users arrive randomly one after the other and that the system has to immediately decide whether the arriving user will participate in the exploration of the new items.

For this setting we present ExcUseMe, a smart exploration algorithm that selects a predefined number of users for exploring new items. ExcUseMe gradually excavates the users that are more likely to be interested in the new items and models the new items based on the users’ interactions. We evaluated ExcUseMe on several datasets and scenarios and compared it to state-of-the-art algorithms. Experimental results indicate that ExcUseMe is an efficient algorithm that outperforms all other algorithms in all tested scenarios.

Session 2b: Cold Start and Hybrid Recommender Systems

Exploiting Geo-Spatial Preference for Personalized Expert Recommendation
by Haokai Lu and James Caverlee

Experts are important for providing reliable and authoritative information and opinion, as well as for improving online reviews and services. While considerable previous research has focused on finding topical experts with broad appeal – e.g., top Java developers, best lawyers in Texas – we tackle the problem of personalized expert recommendation, to identify experts who have special personal appeal and importance to users. One of the key insights motivating our approach is to leverage the geo-spatial preferences of users and the variation of these preferences across different regions, topics, and social communities. Through a fine-grained GPS-tagged social media trace, we characterize these geo-spatial preferences for personalized experts, and integrate these preferences into a matrix factorization-based personalized expert recommender. Through extensive experiments, we find that the proposed approach can improve the quality of recommendation by 24% in precision compared to several baselines. We also find that users’ geo-spatial preference of expertise and their underlying social communities can ameliorate the cold start problem by more than 20% in precision and recall.

Session 2a: Contextual Challenges

Fast Differentially Private Matrix Factorization
by Ziqi Liu, Yu-Xiang Wang and Alexander J. Smola

Differentially private collaborative filtering is a challenging task, both in terms of accuracy and speed. We present a simple algorithm that is provably differentially private, while offering good performance, using a novel connection of differential privacy to Bayesian posterior sampling via Stochastic Gradient Langevin Dynamics. Due to its simplicity the algorithm lends itself to efficient implementation. By careful systems design and by exploiting the power law behavior of the data to maximize CPU cache bandwidth we are able to generate 1024 dimensional models at a rate of 8.5 million recommendations per second on a single PC.

Session 4b: Algorithms

Gaussian Ranking by Matrix Factorization
by Harald Steck

The ranking quality at the top of the list is crucial in many real-world applications of recommender systems. In this paper, we present a novel framework that allows for pointwise as well as listwise training with respect to various ranking metrics. This is based on a training objective function where we assume that, for given a user, the recommender system predicts scores for all items that follow approximately a Gaussian distribution. We motivate this assumption from the properties of implicit feedback data. As a model, we use matrix factorization and extend it by non-linear activation functions, as customary in the literature of artificial neural networks. In particular, we use non-linear activation functions derived from our Gaussian assumption. Our preliminary experimental results show that this approach is competitive with state-of-the-art methods with respect to optimizing the Area under the ROC curve, while it is particularly effective in optimizing the head of the ranked list.

Session 3: Distinguished Papers

HyPER: A Flexible and Extensible Probabilistic Framework for Hybrid Recommender Systems
by Pigi Kouki, Shobeir Fakhraei, James Foulds, Magdalini Eirinaki and Lise Getoor

As the amount of recorded digital information increases, there is a growing need for flexible recommender systems which can incorporate richly structured data sources to improve recommendations. In this paper, we show how a recently introduced statistical relational learning framework can be used to develop a generic and extensible hybrid recommender system. Our hybrid approach, HyPER (HYbrid Probabilistic Extensible Recommender), incorporates and reasons over a wide range of information sources. Such sources include multiple user-user and item-item similarity measures, content, and social information. HyPER automatically learns to balance these different information signals when making predictions. We build our system using a powerful and intuitive probabilistic programming language called probabilistic soft logic, which enables efficient and accurate prediction by formulating our custom recommender systems with a scalable class of graphical models known as hinge-loss Markov random fields. We experimentally evaluate our approach on two popular recommendation datasets, showing that HyPER can effectively combine multiple information types for improved performance, and can outperform existing state-of-the-art approaches.

Session 2b: Cold Start and Hybrid Recommender Systems

‘I like to explore sometimes’: Adapting to Dynamic User Novelty Preferences
by Komal Kapoor, Vikas Kumar, Loren Terveen, Joseph A. Konstan and Paul Schrater

Studies have shown that the recommendation of unseen, novel or serendipitous items is crucial for a satisfying and engaging user experience. As a result, recent developments in recommendation research have increasingly focused towards introducing novelty in user recommendation lists. While, existing solutions aim to ﬁnd the right balance between the similarity and novelty of the recommended items, they largely ignore the user needs for novelty. In this paper, we show that there are large individual and temporal differences in the users’ novelty preferences. We develop a regression model to predict these dynamic novelty preferences of users using features derived from their past interactions. Finally, we describe an adaptive recommender, adaNov-R, that adapts to the user needs for novel items and show that the model achieves better recommendation performance on a metric that considers both novel and familiar items.

Session 1a: The User in the Loop

It Takes Two to Tango: an Exploration of Domain Pairs for Cross-Domain Collaborative Filtering
by Shaghayegh Sahebi and Peter Brusilovsky

As the heterogeneity of data sources are increasing on the web, and due to the sparsity of data in each of these data sources, cross-domain recommendation is becoming an emerging research topic in the recent years. Cross-domain collaborative filtering aims to transfer the user rating pattern from source (auxiliary) domains to a target domain for the purpose of alleviating the sparsity problem and providing better target recommendations. However, the studies so far have either focused on a limited number of domains that are assumed to be related to each other (such as books and movies), or a division of the same dataset (such as movies) into different domains based on an item characteristic (such as genre). In this paper, we study a broad set of domains and their characteristics to understand the factors that affect the success or failure of cross-domain collaborative filtering, the amount of improvement in cross-domain approaches, and the selection of best source domains for a specific target domain. We propose to use Canonical Correlation Analysis (CCA) as a significant major factor in finding the most promising source domains for a target domain, and suggest a cross-domain collaborative filtering based on CCA (CD-CCA) that proves to be successful in using the shared information between domains in the target recommendations.

Session 4a: Novel Setups

Learning Distributed Representations from Reviews for Collaborative Filtering
by Amjad Almahairi, Kyle Kastner, Kyunghyun Cho and Aaron Courville

Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased flexibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model’s ability to act as a regularizer of the product representations.

Session 4a: Novel Setups

Letting Users Choose Recommender Algorithms: An Experimental Study
by Michael D. Ekstrand, Daniel Kluver, F. Maxwell Harper and Joseph A. Konstan

Recommender systems are not one-size-fits-all; different algorithms and data sources have different strengths, making them a better or worse fit for different users and use cases. As one way of taking advantage of the relative merits of different algorithms, we gave users the ability to change the algorithm providing their movie recommendations and studied how they make use of this power. We conducted our study with the launch of a new version of the MovieLens movie recommender that supports multiple recommender algorithms and allows users to choose the algorithm they want to provide their recommendations. We examine log data from user interactions with this new feature to understand whether and how users switch among recommender algorithms, and select a final algorithm to use. We also look at the properties of the algorithms as they were experienced by users and examine their relationships to user behavior.

We found that a substantial portion of our user base (25%) used the recommender-switching feature. The majority of users who used the control only switched algorithms a few times, trying a few out and settling down on an algorithm that they would leave alone. The largest number of users prefer a matrix factorization algorithm, followed closely by item-item collaborative filtering; users selected both of these algorithms much more often than they chose a non-personalized mean recommender. The algorithms did produce measurably different recommender lists for the users in the study, but these differences were not directly predictive of user choice.

Session 1a: The User in the Loop

Overlapping Community Regularization for Rating Prediction in Social Recommender Systems
by Hui Li, Dingming Wu, Wenbin Tang and Nikos Mamoulis

Recommender systems have become de facto tools for suggesting items that are of potential interest to users. Predicting a user’s rating on an item is the fundamental recommendation task. Traditional methods that generate predictions by analyzing the user-item rating matrix perform poorly when the matrix is sparse. Recent approaches use data from social networks to improve accuracy. However, most of the social-network based recommender systems only consider direct friendships and they are less effective when the targeted user has few social connections. In this paper, we propose two alternative models that incorporate the overlapping community regularization into the matrix factorization framework. Our empirical study on four real datasets shows that our approaches outperform the state-of-the-art algorithms in both traditional and social-network based recommender systems regarding both cold-start users and normal users.

Session 1b: Recommender Systems and Social Networks

Predicting Online Performance of News Recommender Systems Through Richer Evaluation Metrics
by Andrii Maksai, Florent Garcin and Boi Faltings

We investigate how metrics that can be measured offine can be used to predict the online performance of recommender systems, thus avoiding costly A-B testing. In addition to accuracy metrics, we combine diversity, coverage, and serendipity metrics to create a new performance model. Using the model, we quantify the trade-off between different metrics and propose to use it to tune the parameters of recommender algorithms without the need for online testing. Another application for the model is a self-adjusting algorithm blend that optimizes a recommender’s parameters over time. We evaluate our findings on data and experiments from news websites.

Session 5a: News and Media

Preference-oriented Social Networks: Group Recommendation and Inference
by Amirali Salehi-Abari and Craig Boutilier

Social networks facilitate a variety of social, economic, and political interactions. Homophily and social influence suggest that preferences (e.g., over products, services, political parties) are likely to be correlated among people whom directly interact in a social network. We develop a model, preference-oriented social networks, that captures such correlations of individual preferences, where preferences take the form of rankings over a set of options. We develop probabilistic inference methods for predicting individual preferences given observed social connections and partial observations of the preferences of others in the network. We exploit these predictions in a social choice context to make group decisions or recommendations even when the preferences of some group members are unobserved. Experiments demonstrate the effectiveness of our algorithms and the improvements made possible by accounting for social ties.

Session 1b: Recommender Systems and Social Networks

PushTrust: An Efficient Recommendation Algorithm by Leveraging Trust and Distrust Relations
by Rana Forsati, Iman Barjasteh, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

The significance of social-enhanced recommender systems is increasing, along with its practicality, as online reviews, ratings, friendship links, and follower relationships are increasingly becoming available. In recent years, there has been an upsurge of interest in exploiting social information, such as trust and distrust relations in recommendation algorithms. The goal is to improve the quality of suggestions and mitigate the data sparsity and the cold-start users problems in existing systems. In this paper, we introduce a general collaborative social ranking model to rank the latent features of users extracted from rating data based on the social context of users. In contrast to existing social regularization methods, the proposed framework is able to simultaneously leverage trust, distrust, and neutral relations, and has a linear dependency on the social network size. By integrating the ranking based social regularization idea into the matrix factorization algorithm, we propose a novel recommendation algorithm, dubbed PushTrust. Our experiments on the Epinions dataset demonstrate that collaboratively ranking the latent features of users by exploiting trust and distrust relations leads to a substantial increase in performance, and to effectively deal with cold-start users problem.

Session 1b: Recommender Systems and Social Networks

Putting Users in Control of their Recommendations
by F. Maxwell Harper, Funing Xu, Harmanpreet Kaur, Kyle Condiff, Shuo Chang and Loren Terveen

The essence of a recommender system is that it can recommend items personalized to the preferences of an individual user. But typically users are given no explicit control over this personalization, and are instead left guessing about how their actions affect the resulting recommendations. We hypothesize that any recommender algorithm will better fit some users’ expectations than others, leaving opportunities for improvement. To address this challenge, we study a recommender that puts some control in the hands of users. Specifically, we build and evaluate a system that incorporates user-tuned popularity and recency modifiers, allowing users to express concepts like “show more popular items”. We find that users who are given these controls evaluate the resulting recommendations much more positively. Further, we find that users diverge in their preferred settings, confirming the importance of giving control to users.

Session 1a: The User in the Loop

Recommending Fair Payments for Large-Scale Social Ridesharing
by Filippo Bistaffa, Alessandro Farinelli, Georgios Chalkiadakis and Sarvapali D. Ramchurn

We perform recommendations for the Social Ridesharing scenario, in which a set of commuters, connected through a social network, arrange one-time rides at short notice. In particular, we focus on how much one should pay for taking a ride with friends. More formally, we propose the first approach that can compute fair coalitional payments that are also stable according to the game-theoretic concept of the kernel for systems with thousands of agents in real-world scenarios. Our tests, based on real datasets for both spatial (GeoLife) and social data (Twitter), show that our approach is significantly faster than the state-of-the-art (up to 84 times), allowing us to compute stable payments for 2000 agents in 50 minutes. We also develop a parallel version of our approach, which achieves a near-optimal speed-up in the number of processors used. Finally, our empirical analysis reveals new insights into the relationship between payments incurred by a user by virtue of its position in its social network and its role (rider or driver).

Session 4a: Novel Setups

Risk-Hedged Venture Capital Investment Recommendation
by Xiaoxue Zhao, Weinan Zhang and Jun Wang

With the increasing accessibility of transactional data in venture finance, venture capital (VC) firms face great challenges in developing quantitative tools to identify new investment opportunities. Recommendation techniques have the possibility of helping VCs making data-driven investment decisions by providing an automatic screening process of the large number of startups across different domains on the basis of their past investment data. A previous study has shown the potential advantage of using collaborative filtering to catch and predict the VCs’ investment behaviours. However, two fundamental challenges in venture finance make conventional recommendation techniques difficult to apply. First, risk factors should be cautiously considered when making investments: for a potential startup, a VC needs to specifically estimate how well this new investment can fit into its holding investment portfolio in such a way that investment risk can be hedged. Second, The investment behaviours are much sparser than conventional recommendation applications and a VC’s investments are usually limited to a few industry categories, making it impossible to use a topic-diversification method to hedge the risk. In this paper, we solve the startup recommendation problem from a risk management perspective. We propose 5 risk-aware startup selection and ranking algorithms to catch the VCs’ investment behaviours and predict their new investments. Apart from the contribution on the new risk-aware recommendation model, our experiments on the collected CrunchBase dataset show significant performance improvements over strong baselines.

Session 2a: Contextual Challenges

Selection and Ordering of Linear Online Video Ads
by Wreetabrata Kar, Viswanathan Swaminathan and Paulo Albuquerque

This paper studies the selection and ordering of in-stream ads in videos shown in online content publishers. We propose an allocation algorithm that uses a collective measure of price and quality for each ad and factors in slot-specific continuation probabilities to maximize publisher revenue. The algorithm is based on cascade models and uses a dynamic programming method to assign linear (video) ads to slots in an online video. The approach accounts for the negative externality created by lower quality ads placed in a video, leading to viewer exit and thereby preventing the publisher from showing the subsequent ads scheduled in that session. Our algorithm is scalable and suited for real-time applications. A large log of viewer activity from a video ad platform is used to empirically test the algorithm. A series of simulations show that our algorithm, when compared to other algorithms currently practiced in industry, generates more revenue for the publisher and increases viewer retention.

Session 5b: E-commerce & Ads

Top-N Recommendation for Shared Accounts
by Koen Verstrepen and Bart Goethals

Standard collaborative filtering recommender systems assume that every account in the training data represents a single user. However, multiple users often share a single account. A typical example is a single shopping account for the whole family. Traditional recommender systems fail in this situation. If contextual information is available, context aware recommender systems are the state-of-the-art solution. Yet, often no contextual information is available. Therefore, we introduce the challenge of recommending to shared accounts in the absence of contextual information. We propose a solution to this challenge for all cases in which the reference recommender system is an item-based top-N collaborative filtering recommender system, generating recommendations based on binary, positive-only feedback. We experimentally show the advantages of our proposed solution for tackling the problems that arise from the existence of shared accounts on multiple datasets.

Session 2a: Contextual Challenges

List of all short papers accepted for RecSys 2015 (in alphabetical order).

No matches were found!

A Study of Priors for Relevance-Based Language Modelling of Recommender Systems
by Daniel Valcarce, Javier Parapar and Álvaro Barreiro

Probabilistic modelling of recommender systems naturally introduces the concept of prior probability into the recommendation task. Relevance-Based Language Models, a principled probabilistic query expansion technique in Information Retrieval, has been recently adapted to the item recommendation task with success. In this paper, we study the effect of the item and user prior probabilities under that framework. We adapt two priors from the document retrieval field and then we propose other two new probabilistic priors. Evidence gathered from experimentation indicates that a linear prior for the neighbour and a probabilistic prior based on Dirichlet smoothing for the items improve the quality of the item recommendation ranking.

Adapting Recommendations to Contextual Changes Using Hierarchical Hidden Markov Models
by Mehdi Hosseinzadeh Aghdam, Negar Hariri, Bamshad Mobasher and Robin Burke

Recommender systems help users find items of interest by tailoring their recommendations to users’ personal preferences. The utility of an item for a user, however, may vary greatly depending on that user’s specific situation or the context in which the item is used. Without considering these changes in preferences, the recommendations may match the general preferences of a user, but they may have small value for the user in his/her current situation. In this paper, we introduce a hierarchical hidden Markov model for capturing changes in user’s preferences. Using a user’s feedback sequence on items, we model the user as a hierarchical hidden Markov process and the current context of the user as a hidden variable in this model. For a given user, our model is used to infer the maximum likelihood sequence of transitions between contextual states and to predict the probability distribution for the context of the next action. The predicted context is then used to generate recommendations. Our evaluation results using Last.fm music playlist data, indicate that this approach achieves significantly better performance in terms of accuracy and diversity compared to baseline methods.

Are Real-World Place Recommender Algorithms Useful in Virtual World Environments?
by Leandro Balby Marinho, Christoph Trattner and Denis Parra

Large scale virtual worlds such as massive multiplayer online games or 3D worlds gained tremendous popularity over the past few years. With the large and ever increasing amount of content available, virtual world users face the information overload problem. To tackle this issue, game-designers usually deploy recommendation services with the aim of making the virtual world a more joyful environment to be connected at. In this context, we present in this paper the results of a project that aims at understanding the mobility patterns of virtual world users in order to derive place recommenders for helping them to explore content more efficiently. Our study focus on the virtual world SecondLife, one of the largest and most prominent in recent years. Since SecondLife is comparable to real-world Location-based Social Networks (LBSNs), i.e., users can both check-in and share visited virtual places, a natural approach is to assume that place recommenders that are known to work well on real-world LBSNs will also work well on SecondLife. We have put this assumption to the test and found out that (i) while collaborative filtering algorithms have compatible performances in both environments, (ii) existing place recommenders based on geographic metadata are not useful in SecondLife.

Asymmetric Recommendations: The Interacting Effects of Social Ratings’ Direction and Strength on Users’ Ratings
by Oded Nov and Ofer Arazy

In social recommendation systems, users often publicly rate objects such as photos, news articles or consumer products. When they appear in aggregate, these ratings carry social signals such as the direction and strength of the raters’ average opinion about the product. Using a controlled experiment we manipulated two central social signals – the direction and strength of social ratings of five popular consumer products – and examined their interacting effects on users’ ratings. The results show an asymmetric user behavior, where the direction of perceived social rating has a negative effect on users’ ratings if the direction of perceived social rating is negative, but no effect if the direction is positive. The strength of perceived social ratings did not have a significant effect on users’ ratings. The findings highlight the potential for cascading adverse effects of small number of negative user ratings on subsequent users’ opinions.

Crowd Sourcing, with a Few Answers: Recommending Commuters for Traffic Updates
by Elizabeth M. Daly, Michele Berlingerio and François Schnitzler

Real-time traffic awareness applications are playing an ever increasing role understanding and tackling traffic congestion in cities. First-hand accounts from drivers witnessing an incident is an invaluable source of information for traffic managers. Nowadays, drivers increasingly contact control rooms through social media to report on journey times, accidents or road weather conditions. These new interactions allow traffic controllers to engage users, and in particular to query them for information rather than passively collecting it. Querying articipants presents the challenge of which users to probe for updates about a specific situation. In order to maximise the probability of a user responding and the accuracy of the information, we propose a strategy which takes into account the engagement levels of the user, the mobility profile and the reputation of the user. We provide an analysis of a real-world user corpus of Twitter users contributing updates to LiveDrive, a Dublin based traffic radio station.

Data Quality Matters in Recommender Systems
by Oren Sar Shalom, Shlomo Berkovsky, Royi Ronen, Elad Ziklik and Amir Amihood

Although data quality has been recognized as an important factor in the broad information systems research, it has received little attention in recommender systems. Data quality matters are typically addressed in recommenders by ad-hoc cleansing methods, which prune noisy or unreliable records from the data. However, the setting of the cleansing parameters is often done arbitrarily, without thorough consideration of the data characteristics. In this work, we turn to two central data quality problems in recommender systems: sparsity and redundancy. We devise models for setting data-dependent thresholds and sampling levels, and evaluate these using a collection of public and proprietary datasets. We observe that the models accurately predict data cleansing parameters, while having minor effect on the accuracy of the generated recommendations.

Elsevier Journal Finder: Recommending Journals for your Paper
by Ning Kang, Marius Doornenbal and Bob Schijvenaars

Rejection is the norm in academic publishing. One of the main reasons for rejections is that the topics of the submitted papers are not relevant to the scope of the journal, even when the papers themselves are excellent. Submission to a journal that fits well with the publication may avoid this issue. A system that is able to suggest journals that have published similar articles to the submitted papers may help authors choose where to submit. The Elsevier journal finder, a freely available online service, is one of the most comprehensive journal recommender systems, covering all scientific domains and more than 2,900 per-reviewed Elsevier journals. The system uses natural language processing for feature generation, and Okapi BM25 matching for the recommendation algorithm. The procedure is to paste text, such as an abstract, and get a list of recommend journals and relevant metadata. The website URL is http://journalfinder.elsevier.com.

Evaluating Tag Recommender Algorithms in Real-World Folksonomies: A Comparative Study
by Dominik Kowald and Elisabeth Lex

To date, the evaluation of tag recommender algorithms has mostly been conducted in limited ways, including p-core pruned datasets, a small set of compared algorithms and solely based on recommender accuracy. In this study, we use an open-source evaluation framework to compare a rich set of state-of-the-art algorithms in six unfiltered, open datasets via various metrics, measuring not only accuracy but also the diversity, novelty and computational costs of the approaches. We therefore provide a transparent and reproducible tag recommender evaluation in real-world folksonomies. Our results suggest that the efficacy of an algorithm highly depends on the given needs and thus, they should be of interest to both researchers and developers in the field of tag-based recommender systems.

Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social Tagging
by Santiago Larrain, Christoph Trattner, Denis Parra, Eduardo Graells-Garrido and Kjetil Nørvåg

In this paper, we present work-in-progress of a recently started project that aims at studying the effect of time in recommender systems in the context of social tagging. Despite the existence of previous work in this area, no research has yet made an extensive evaluation and comparison of time-aware recommendation methods. With this motivation, this paper presents results of a study where we focused on understanding (i) “when” to use the temporal information into traditional collaborative filtering (CF) algorithms, and (ii) “how” to weight the similarity between users and items by exploring the effect of different time-decay functions. As the results of our extensive evaluation conducted over five social tagging systems (Delicious, BibSonomy, CiteULike, MovieLens, and Last.fm) suggest, the step (when) in which time is incorporated in the CF algorithm has substantial effect on accuracy, and the type of time-decay function (how) plays a role on accuracy and coverage mostly under pre-filtering on user-based CF, while item-based shows stronger stability over the experimental conditions.

Improving the User Experience during Cold Start through Choice-Based Preference Elicitation
by Mark P. Graus and Martijn C. Willemsen

We studied an alternative choice-based interface for preference elicitation during the cold start phase and compared it directly with a standard rating-based interface. In this alternative interface users started from a diverse set covering all movies and iteratively narrowed down through a matrix factorization latent feature space to smaller sets of items based on their choices. The results show that compared to a rating-based interface, the choice-based interface requires less effort and results in more satisfying recommendations, showing that it might be a promising candidate for alleviating the cold start problem of new users.

Incremental Matrix Factorization via Feature Space Re-learning for Recommender System
by Qiang Song, Jian Cheng and Hanqing Lu

Matrix factorization is widely used in Recommender Systems. Although existing popular incremental matrix factorization methods are effectively in reducing time complexity, they simply assume that the similarity between items or users is invariant. For instance, they keep the item feature matrix unchanged and just update the user matrix without re-training the entire model. However, with the new users growing continuously, the fitting error would be accumulated since the extra distribution information of items has not been utilized. In this paper, we present an alternative and reasonable approach, with a relaxed assumption that the similarity between items (users) is relatively stable after updating. Concretely, utilizing the prediction error of the new data as the auxiliary features, our method updates both feature matrices simultaneously, and thus users’ preference can be better modeled than merely adjusting one corresponded feature matrix. Besides, our method maintains the feature dimension in a smaller size through taking advantage of matrix sketching. Experimental results show that our proposal outperforms the existing incremental matrix factorization methods.

Latent Trajectory Modeling: A Light and Efficient Way to Introduce Time in Recommender Systems
by Elie Guàrdia-Sebaoun, Vincent Guigue and Patrick Gallinari

For recommender systems, time is often an important source of information but it is also a complex dimension to apprehend. We propose here to learn item and user representations such that any timely ordered sequence of items selected by a user will be represented as a trajectory of the user in a representation space. This allows us to rank new items for this user. We then enrich the item and user representations in order to perform rating prediction using a classical matrix factorization scheme. We demonstrate the interest of our approach regarding both item ranking and rating prediction on a series of classical benchmarks.

Making the Most of Preference Feedback by Modeling Feature Dependencies
by S Chandra Mouli and Sutanu Chakraborty

Conversational recommender systems help users navigate through the product space by exploiting feedback. In conversational systems based on preference-based feedback, the user selects the most preferred item from a list of recommended products. Modelling user’s preferences then becomes important in order to recommend relevant items. Several existing recommender systems accomplish this by assuming the features to be independent. Here we will attempt to forego this assumption and exploit the dependencies between the features to build a robust user preference model.

Nudging Grocery Shoppers to Make Healthier Choices
by Elizabeth Wayman and Sriganesh Madhvanath

Despite the rampant increase in obesity rates and concomitant increases in rates of mortality from heart disease, cancer and diabetes, getting the general public to adopt a healthy diet has proven to be challenging for a variety of reasons. In this paper, we describe Foodle, a research project aimed at providing automated, personalized and goal-driven dietary guidance to users based on their grocery receipt data, by leveraging the availability of digital receipts for grocery store purchases. We discuss challenges faced, the current state of the project, and directions for future work.

Nuke `Em Till They Go: Investigating Power User Attacks to Disparage Items in Collaborative Recommenders
by Carlos E. Seminario and David C. Wilson

Recommender Systems (RSs) can be vulnerable to manipulation by malicious users who successfully bias recommendations for their own benefit or pleasure. These are known as attacks on RSs and are typically used to either promote (“push”) or disparage (“nuke”) targeted items contained within the recommender’s user-item dataset. Our recent work with the Power User Attack (PUA) attack model, determined that attackers disguised as influential power users can mount successful (from the attacker’s viewpoint) push attacks against user-based, item-based, and SVD-based recommenders. However, the success of push attack vectors may not be symmetric for nuke attacks, which target the opposite effect — reducing the likelihood that target items appear in users’ top-N lists. The asymmetry between push and nuke attacks is highlighted when evaluating these attacks using traditional robustness metrics such as Rank and Prediction Shift. This paper examines the PUA attack model in the context of nuke attacks, in order to investigate the differences between push and nuke attack orientations, as well as how they are evaluated. In this work we show that the PUA is able to mount successful nuke attacks against commonly-used recommender algorithms highlighting the “nuke vs. push” asymmetry in the results.

‘Please, Not Now!’ A Model for Timing Recommendations
by Nofar Dali Betzalel, Bracha Shapira and Lior Rokach

Proactive recommender systems push recommendations to users without their explicit request whenever a recommendation that suits a user is available. These systems strive to optimize the match between recommended items and users’ preferences. We assume that recommendations might be reflected with low accuracy not only due to the recommended items’ suitability to the user, but also because of the recommendations’ timings. We therefore claim that it is possible to learn a model of good and bad contexts for recommendations that can later be integrated in a recommender system. Using mobile data collected during a three weeks user study we suggest a two-phase model that is able to classify whether a certain context is at all suitable for any recommendation, regardless of its content. Results reveal that a hybrid model that first decides whether it should use a personal or a non-personal timing model, and then classifies accordingly whether the timing is proper for recommendations, is superior to both the personal or non-personal timing models.

POI Recommendation: Towards Fused Matrix Factorization with Geographical and Temporal Influences
by Jean-Benoît Griesner, Talel Abdessalem and Hubert Naacke

Providing personalized point-of-interest (POI) recommendation has become a major issue with the rapid emergence of location-based social networks (LBSNs). Unlike traditional recommendation approaches, the LBSNs application domain comes with significant geographical and temporal dimensions. Moreover most of traditional recommendation algorithms fail to cope with the specific challenges implied by these two dimensions. Fusing geographical and temporal influences for better recommendation accuracy in LBSNs remains unexplored, as far as we know. We depict how matrix factorization can serve POI recommendation, and propose a novel attempt to integrate both geographical and temporal influences into matrix factorization. Specifically we present GeoMF-TD, an extension of geographical matrix factorization with temporal dependencies. Our experiments on a real dataset shows up to 20% benefit on recommendation precision.

The Recommendation Game: Using a Game-with-a-Purpose to Generate Recommendation Data
by Sam Banks, Rachael Rafter and Barry Smyth

This paper describes a casual Facebook game to capture recommendation data as a side-effect of gameplay. We show how this data can be used to make successful recommendations as part of a live-user trial.

Top-N Recommendation with Missing Implicit Feedback
by Daryl Lim, Julian McAuley and Gert Lanckriet

In implicit feedback datasets, non-interaction of a user with an item does not necessarily indicate that an item is irrelevant for the user. Thus, evaluation measures computed on the observed feedback may not accurately reflect performance on the complete data. In this paper, we discuss a missing data model for implicit feedback and propose a novel evaluation measure oriented towards Top-N recommendation. Our evaluation measure admits unbiased estimation under our missing data model, unlike the popular Normalized Discounted Cumulative Gain (NDCG) measure. We also derive an efficient algorithm to optimize the measure on the training data. We run several experiments which demonstrate the utility of our proposed measure.

Towards Automatic Meal Plan Recommendations for Balanced Nutrition
by David Elsweiler and Morgan Harvey

Food recommenders have been touted as a useful tool to help people achieve a healthy diet. Here we incorporate nutrition into the recommender problem by examining the feasibility of algorithmically creating daily meal plans for a sample of user profiles (n=100), combined with a diverse set of food preference data (n=64) collected in a natural setting. Our analyses demonstrate it is possible to recommend plans for a large percentage of users which meet the guidelines set out by international health agencies.

Uncovering Systematic Bias in Ratings across Categories: a Bayesian Approach
by Fangjian Guo and David B. Dunson

Recommender systems are routinely equipped with standardized taxonomy that associates each item with one or more categories or genres. Although such information does not directly imply the quality of an item, the distribution of ratings vary greatly across categories, e.g. animation movies may generally receive higher ratings than action movies. While it is a natural outcome given the diversity and heterogeneity of both users and items, it makes directly aggregated ratings, which are commonly used to guide users’ choice by reflecting the overall quality of an item, incomparable across categories and hence prone to fairness and diversity issues. This paper aims to uncover and calibrate systematic category-wise biases for discrete-valued ratings. We propose a novel Bayesian multiplicative probit model that treats the inflation or deflation of mean rating for a combination of categories as multiplicatively contributed from category-specific parameters. The posterior distribution of those parameters, as inferred from data, can capture the bias for all possible combinations of categories, thus enabling statistically efficient estimation and principled rating calibration.

User Churn Migration Analysis with DEDICOM
by Rafet Sifa, César Ojeda and Christian Bauckhage

Time plays an important role regarding user preferences for products. It introduces asymmetries into the adoption of products which should be considered the context of recommender systems and business intelligence. We therefore investigate how temporally asymmetric user preferences can be analyzed using a latent factor model called Decomposition Into Directional Components (DEDICOM). We introduce a new scalable hybrid algorithm that combines projected gradient descent and alternating least squares updates to compute DEDICOM and imposes semi-nonnegativity constraints to better interpret the resulting factors. We apply our model to analyze user churn and migration between different computer games in a social gaming environment.

Short papers are pitched in the Short Paper and Demo Slam. Afterwards, posters of short papers are exhibited during the reception and then in the designated poster area.

List of all demos accepted for RecSys 2015 (in alphabetical order).

A Personalised Reader for Crowd Curated Content
by Gabriella Kazai, Daoud Clarke, Iskander Yusof and Matteo Venanzi

Personalised news recommender systems traditionally rely on content ingested from a select set of publishers and ask users to indicate their interests from a predefined list of topics. They then provide users a feed of news items for each of their topics. In this demo, we present a mobile app that automatically learns users’ interests from their browsing or twitter history and provides them with a personalised feed of diverse, crowd curated content. The app also continuously learns from the users’ interactions as they swipe to like or skip items recommended to them. In addition, users can discover trending stories and content liked by other users they follow. The crowd is thus formed of the users, who as a whole act as the curators of the content to be recommended.
Automated Recommendation of Healthy, Personalised Meal Plans
by Morgan Harvey and David Elsweiler

Poor health due to a lack of understanding of nutrition is a major problem in the modern world, one which could potentially be addressed via the use of recommender systems. In this demo we present a system to generate meal plans for users which they will not only like, based on their taste preferences, but will also conform to daily nutritional guidelines. The interface allows the selection of recipes for breakfast, lunch and dinner and can automatically complete a daily meal plan or can generate entire plans itself.
CNARe: Co-authorship Networks Analysis and Recommendations
by Guilherme A. de Sousa, Matheus A. Diniz, Michele A. Brandão and Mirella M. Moro

We present CNARe, an easy-to-use online system that shows personalized collaboration recommendations to researchers. It also provides visualizations and metrics that allow to investigate how the recommendations affect a co-authorship network and other analyses.
Event Recommendation using Twitter Activity
by Axel Magnuson, Vijay Dialani and Deepa Mallela

User interactions with Twitter (social network) frequently take place on mobile devices – a user base that it strongly caters to. As much of Twitter’s traffic comes with geotagging information associated with it, it is a natural platform for geographic recommendations. This paper proposes an event recommender system for Twitter users, which identifies twitter activity co-located with previous events, and uses it to drive geographic recommendations via item-based collaborative filtering.
Health-aware Food Recommender System
by Mouzhi Ge, Francesco Ricci and David Massimo

With the rapid changes in the food variety and lifestyles, many people are facing the problem of making healthier food decisions to reduce the risk of chronic diseases such as obesity and diabetes. To this end, our recommender system not only offers recipe recommendations that suit the user’s preference but is also able to take the user’s health into account. It is developed on a mobile platform by considering that our application may be directly used in the kitchen. This demo paper summarizes the complete human-computer interaction design, the implemented health-aware recommendation algorithm and preliminary user feedback.
Kibitz: End-to-End Recommendation System Builder
by Quanquan Liu and David R. Karger

Kibitz (kibitz.csail.mit.edu) is a web application and recommendation system framework that helps inexperienced and novice programmers to build recommenders without the need to program the back end for the system. The author uploads a table of items, and Kibitz produces a collaborative-filtering recommender for the uploaded items. The recommender can be hosted by Kibitz or downloaded and customized as a set of static pages hosted on the author’s personal web domain. Developers who want to avoid the hassle of writing their own recommender back end may choose to link their websites to our service through our easy to use API. A demo of our system can be found at kibitz.csail.mit.edu/video_demo/.
OSMRec Tool for Automatic Recommendation of Categories on Spatial Entities in OpenStreetMap
by Nikos Karagiannakis, Giorgos Giannopoulos, Dimitrios Skoutas and Spiros Athanasiou

In this demonstration, we present OSMRec, a command line utility and JOSM plugin for automatic recommendation of tags (categories) on newly created spatial entities in OpenStreetMap (OSM). JOSM allows downloading parts of OSM, editing the map (e.g. inserting, deleting, annotating with tags spatial entities) and re-uploading the updated part back on OSM. OSMRec plugin exploits already annotated entities within OSM to train category classification models and utilizes these models in order to recommend OSM categories for newly inserted spatial entities in OSM.

Demos are pitched in the Short Paper and Demo Slam. Afterwards, demos are exhibited during the reception. Posters of the demos are then exhibited in the designated poster area.

List of all posters accepted for RecSys 2015 (in alphabetical order).
Poster proceedings are available at CEUR-WS.org.

No matches were found!

A Recommendation-Based Book-Exchange System Without Using Wish Lists
by Maria Soledad Pera and Yiu-Kai Ng

We introduce EasyEx, a recommendation-based book exchange system which identifies potential exchanges for a user solely based on the user’s item list. EasyEx is novel, since it effectively identifies books that are likely appealing to users, and optimizes book-exchange cycles to increase serendipity, instead of simply swapping books on users’ wish lists as performed by existing item-exchange algorithms. Experimental results have verified that EasyEx others users recommended books that satisfy their interests and contributes to the item-exchange mechanism with a new design methodology.

Analysing Compression Techniques for In-Memory Collaborative Filtering
by Saúl Vargas, Craig Macdonald and Iadh Ounis

Following the recent trend of in-memory data processing, it is a usual practice to maintain collaborative filtering data in the main memory when generating recommendations in academic and industrial recommender systems. In this paper, we study the impact of integer compression techniques for in-memory collaborative filtering data in terms of space and time efficiency. Our results provide relevant observations about when and how to compress collaborative filtering data. First, we observe that, depending on the memory constraints, compression techniques may speed up or slow down the performance of state-of-the-art collaborative filtering algorithms. Second, after comparing different compression techniques, we find the Frame of Reference (FOR) technique to be the best option in terms of space and time efficiency under different memory constraints.

Analysis of User-generated Content for Improving YouTube Video Recommendation
by Michele Galli, Davide Feltoni Gurini, Fabio Gasparetti, Alessandro Micarelli and Giuseppe Sansonetti

Everyday video-sharing websites such as YouTube collect large amounts of new multimedia resources. Comments left by viewers often provide valuable information to describe sentiments, opinions and tastes of users. For this reason, we propose a novel re-ranking approach that takes into consideration that information in order to provide better recommendations of related videos. Early experiments indicate an improvement in the recommendation performance.

Comparing offline and online recommender system evaluations on long-tail distributions
by Gabriel de Souza Pereira Moreira, Gilmar Alves de Souzaand, Adilson Cunha

In this investigation, we conduct a comparison between offline and online accuracy evaluation of different algorithms and settings in a real-world content recommender system. By focusing on recommendations of long-tail items, which are usually more interesting for users, it was possible to reduce the bias caused by extremely popular items and to observe a better alignment of accuracy results in offline and online evaluations.

Do you have a Pop face? Here is a Pop song. Using profile pictures to mitigate the cold-start problem in Music Recommender Systems.
by Eugenio Tacchini, Ramon Morros, Veronica Vilaplana and Enrique Sañoso

When a new user registers to a recommender system service, the system does not know her taste and cannot propose meaningful suggestions (cold-start problem). This preliminary work attempts to mitigate the cold-start problem using the profile picture of the user as a sole information, following the intuition that a correspondence may exist between the pictures that people use to represent themselves and their taste. We proved that, at least in the small music community we used for our experiments, our method can improve the precision of both a classifier and a Top-N music recommender system in a cold-start condition.

Exploiting Latent Social Listening Representations for Music Recommendations
by Chih-Ming Chen, Po-Chuan Chien, Yu-Ching Lin, Ming-Feng Tsai and Yi-Hsuan Yang

Music listening can be regarded as a social activity, in which people can listen together and make friends with one other. Therefore, social relationships may imply multiple facets of the users, such as their listening behaviors and tastes. In this light, it is considered that social relationships hold abundant valuable information that can be utilized for music recommendation. However, utilizing the information for recommendation could be difficult, because such information is usually sparse. To address this issue, we propose to learn the latent social listening representations by the DeepWalk method, and then integrate the learned representations into Factorization Machines to construct better recommendation models. With the DeepWalk method, user social relationships can be transformed from the sparse and independent and identically distributed (i.i.d.) form into a dense and non-i.i.d. form. In addition, the latent representations can also capture the spatial locality among users and items, therefore benefiting the constructed recommendation models.

Exploiting Reviews to Guide Users’ Selections
by Nevena Dragovic and Maria Soledad Pera

We introduce HRS, a recommender that exploits user reviews and identifies the features that are most likely appealing to users. HRS incorporates this knowledge into the recommendation process to generate a list of top-k recommendations, each of which is paired with an explanation that (i) showcases why a particular item was recommended and (ii) helps users decide which items, among the ones recommended, are best tailored towards their individual interests. Empirical studies conducted using the Amazon dataset demonstrate the correctness of the proposed methodology.

How to Interpret Implicit User Feedback?
by Ladislav Peska and Peter Vojtas

Our research is focused on interpreting user preference from his/her implicit behavior. There are many types of relevant behavior e.g. time on page, scrolling, clickstream etc. which we will further denote as Relevant Behavior Types (RBT). RBT s varies both in quality and incidence and thus we might need different approaches to process them. In this early work we focus on how to derive user preference from each RBT separately. We selected number of common indicators, design two novel e-commerce specific RBT interpreting methods and conducted series of offline experiments. After the off-line evaluation an A/B test on the real-world users of a travel agency was conducted comparing best off-line method with simple binary feedback. The experiments, although preliminary, showed importance of considering multiple RBTs together.

Image Discovery and Insertion for Custom Publishing
by Lei Liu, Jerry Liu and Shanchan Wu

Images in reading materials make the content come alive. Aside from providing additional information to the text, reading material containing illustration engages our spatial memory, increases memory retention of the material. However, despite the plethora of available multimedia, adding illustrations to text continues to be a difficult task for the amateur content publisher. To address this problem, we present a semantic-aware image discovery and insertion system for custom publishing. Compared to image search engines, our system has the advantage of being able to discern among different topics within a long text passage and recommend the most relevant images for each detected topic with semantic “visual words” based relevance.

Item Familiarity Effects in User-Centric Evaluations of Recommender Systems
by Dietmar Jannach, Lukas Lerche and Michael Jugovac

Laboratory studies are a common way of comparing recommendation approaches with respect to different quality dimensions that might be relevant for real users. One typical experimental setup is to first present the participants with recommendation lists that were created with different algorithms and then ask the participants to assess these recommendations individually or to compare two item lists. The cognitive effort required by the participants for the evaluation of item recommendations in such settings depends on whether or not they already know the (features of the) recommended items. Furthermore, lists containing popular and broadly known items are correspondingly easier to evaluate.

In this paper we report the results of a user study in which participants recruited on a crowdsourcing platform assessed system-provided recommendations in a between-subjects experimental design. The results surprisingly showed that users found non-personalized recommendations of popular items the best match for their preferences. An analysis revealed a measurable correlation between item familiarity and user acceptance. Overall, the observations indicate that item familiarity can be a potential confounding factor in such studies and should be considered in experimental designs.

Measuring the Concentration Reinforcement Bias of Recommender Systems
by Panagiotis Adamopoulos, Alexander Tuzhilin and Peter Mountanos

In this paper, we propose new metrics to accurately measure the concentration reinforcement of recommender systems and the enhancement of the “long tail”. We also conduct a comparative analysis of various RS algorithms illustrating the usefulness of the proposed metrics.

Merging Latent Factors and Tags to Increase Interactive Control of Recommendations
by Tim Donkers, Benedikt Loepp and Jürgen Ziegler

We describe a novel approach that integrates user-generated tags with standard Matrix Factorization to allow users to interactively control recommendations. The tag information is incorporated during the learning phase and relates to the automatically derived latent factors. Thus, the system can change an item’s score whenever the user adjusts a tag’s weight. We implemented a prototype and performed a user study showing that this seems to be a promising way for users to interactively manipulate the set of items recommended based on their user profile or in cold-start situations.

30Music listening and playlists dataset
by Roberto Turrin, Massimo Quadrana, Andrea Condorelli, Roberto Pagano and Paolo Cremonesi

We introduce the 30Music dataset, a collection of listening and playlists data retrieved from Internet radio stations through Last.fm API. In this paper we describe the creation process, its content, and its possible uses. Attractive features of the 30Music dataset that differentiate it from existing public datasets include, among the others, (i) the user listening sessions complete of contextual time information, (ii) the user playlists, and (iii) the positive user ratings, key information to experiment with the task of modeling user taste and recommending playlists.

Network-Based Extension of Multi-Relational Factorization Models
by Fatemeh Vahedian, Robin Burke and Bamshad Mobasher

Complex heterogeneous networks contain many types of relations, both local to a particular entity and distant in the network. Multi-relational factorization schemes that incorporate multiple local relations have shown improved recommendation accuracy. This paper extends this prior work on multi-relational factorization to include extended relations derived from network data and demonstrates improved accuracy for these extended hybrids.

Next Basket Recommendation with Neural Networks
by Shengxian Wan, Yanyan Lan, Pengfei Wang, Jiafeng Guo, Jun Xu and Xueqi Cheng

One crucial task in recommendation is to predict what a user will buy next given her shopping history. In this paper, we propose a novel neural network to complete this task. The model consists of an embedding layer, a hidden layer and an output layer. Firstly, the distributed representations of the user and the items bought before are obtained and used to form a feature vector by the embedding layer. Then the hidden layer transforms the feature vector to another space by a non-linear operator. Finally, the softmax operator is adopted to output the probabilities of next items. We can see that the model elegantly involves both the user’s general interest and the sequential dependencies between items for prediction. Experimental results on two real datasets prove the effectiveness of our model.

Personality-Based Recommendations: Evidence from Amazon.com
by Panagiotis Adamopoulos and Vilma Todri

In this paper, we evaluate the accuracy of personality-based recommendations using a real-world data set from Amazon.com. We automatically infer the personality traits, needs, and values of users based on unstructured user-generated content in social media, rather than administering questionnaires or explicitly asking the users to self-report their characteristics. We find that personality characteristics significantly increase the performance of recommender systems, in general, while different personality models exhibit statistically significant differences in predictive performance.

Recommendation with the Right Slice: Speeding Up Collaborative Filtering with Factorization Machines
by Babak Loni, Martha Larson, Alexandros Karatzoglou and Alan Hanjalic

We propose an alternative way to efficiently exploit rating data for collaborative filtering with Factorization Machines (FMs). Our approach partitions user-item matrix into ‘slices’ which are mutually exclusive with respect to items. The training phase makes direct use of the slice of interest (target slice), while incorporating information from other slices indirectly. FMs represent user-item interactions as feature vectors, and they offer the advantage of easy incorporation of complementary information. We exploit this advantage to integrate information from other auxiliary slices. We demonstrate, using experiments on two benchmark datasets, that improved performance can be achieved, while the time complexity of training can be reduced significantly.

Recommendations to Enhance Children Web Searches
by Shahrzad Karimi and Maria Soledad Pera

We present the initial design and development of KidsQR, a query recommendation system tailored exclusively for children. KidsQR aids children in their quest for online information by considering children vocabulary, child-friendly phrases, and entities children are familiar with. Initial experiments conducted based on the assessment of parents and elementary school teacher appraisers verify the promising performance of KidsQR.

Recommender Systems for Product Bundling
by Moran Beladev, Bracha Shapira and Lior Rokach

Recommender systems (RSs) enhance e-commerce sales by recommending relevant products to their customers. RSs aim at implementing the firm’s web-based marketing strategy to increase revenues. Generating bundles is an example of a marketing strategy that aims to satisfy consumer needs and preferences, and at the same time, to increase customers’ buying scope and the firm’s income. Thus, finding and recommending an optimal and personal bundle becomes very important. In this paper we introduce a novel model of bundle recommendations that integrates collaborative filtering (CF) techniques, personalized demand functions, and price modeling. This model provides a recommendation list by finding pairs of products that maximizes both, the probability of their purchase by the user and the revenue received by selling this bundles.

Style Recommendation for Fashion Items using Heterogeneous Information Network
by Hanbit Lee and Sang-Goo Lee

In the midst of vast amounts of available fashion items, consumers today require more efficient recommendation services. A system that sorts out items that form a stylish ensemble with already selected or possessed items would provide them with greater convenience. In this paper, we propose a fashion item recommendation method that learns the way the fashion items are matched from a large ensemble database. We empirically show that the proposed method can explain factors that affect item matching and recommend the most suitable items to the given set of items.

Tackling Cold-Start Users in Recommender Systems with Indoor Positioning Systems
by Emanuel Lacic, Dominik Kowald, Matthias Traub, Granit Luzhnica, Joerg Simon and Elisabeth Lex

In this paper, we present work-in-progress on a recommender system based on Collaborative Filtering that exploits location information gathered by indoor positioning systems. This approach allows us to provide recommendations for “extreme” cold-start users with absolutely no item interaction data available, where methods based on Matrix Factorization would not work. We simulate and evaluate our proposed system using data from the location-based FourSquare system and show that we can provide substantially better recommender accuracy results than a simple MostPopular baseline that is typically used when no interaction data is available.

Towards Improving Top-N Recommendation by Generalization of SLIM
by Santiago Larrain, Denis Parra and Alvaro Soto

Sparse Linear Methods (SLIM) are state-of-the-art recommendation approaches based on matrix factorization, which rely on a regularized l1-norm and l2-norm optimization — an alternative optimization problem to the traditional Frobenious norm. Although they have shown outstanding performance in Top-N recommendation, existent works have not yet analyzed some inherent assumptions that can have an important effect on the performance of these algorithms. In this paper, we attempt to improve the performance of SLIM by proposing a generalized formulation of the aforementioned assumptions. Instead of directly learning a sparse representation of the user-item matrix, we (i) learn the latent factors’ matrix of the users and the items via a traditional matrix factorization approach, and then (ii) reconstruct the latent user or item matrix via prototypes which are learned using sparse coding, an alternative SLIM commonly used in the image processing domain. The results show that by tuning the parameters of our generalized model we are able to outperform SLIM in several Top-N recommendation experiments conducted on two different datasets, using both nDCG and nDCG@10 as evaluation metrics. These preliminary results, although not conclusive, indicate a promising line of research to improve the performance of SLIM recommendation.

Word Embedding techniques for Content-based Recommender Systems: an empirical evaluation
by Cataldo Musto, Giovanni Semeraro, Marco De Gemmis and Pasquale Lops

This work presents an empirical comparison among three widespread word embedding techniques as Latent Semantic Indexing, Random Indexing and the more recent Word2Vec. Specifically, we employed these techniques to learn a low-dimensional vector space word representation and we exploited it to represent both items and user profiles in a content-based recommendation scenario. The performance of the techniques has been evaluated against two state-of-the-art datasets, and experimental results provided good insights which pave the way to several future directions.

Posters are exhibited during the reception and then in the designated poster area.

Back to Program