- DMA Low-Code Tool Supporting the Development of Recommender Systems
by Claudio Di Sipio (Università degli Studi dell’Aquila, Italy), Juri Di Rocco (Università degli Studi Dell”Aquila, Italy), Davide Di Ruscio (Università degli Studi dell’Aquila, Italy), and Dr. Phuong Thanh Nguyen (Università degli Studi dell’Aquila, Italy)
The design of recommender systems (RSs) to support software development encompasses the fulfillment of different steps, including data preprocessing, choice of the most appropriate algorithms, item delivery. Though RSs can alleviate the curse of information overload, existing approaches resemble black-box systems, in which the end-user is not expected to fine-tune or personalize the overall process.
In this work, we propose LEV4REC, a low-code environment to assist developers in designing, configuring, and delivering recommender systems. The first step supported by the proposed tool includes defining an initial model that allows for the configuration of the crucial components of the wanted RS. Then, a subsequent phase is performed to finalize the RS design, e.g., to specify configuration parameters. LEV4REC is eventually capable of generating source code for the desired RS. To evaluate the capabilities of the approach, we used LEV4REC to specify two existing RSs built on top of two different recommendation algorithms, i.e., collaborative filtering and supervised machine learning.
Full text in ACM Digital Library
|
- DMThe role of preference consistency, defaults and musical expertise in users’ exploration behavior in a genre exploration recommender
by Yu Liang (Jheronimus Academy of Data Science, Netherlands) and Martijn C. Willemsen (Eindhoven University of Technology and Jheronimus Academy of Data Science, Netherlands)
Recommender systems are efficient at predicting users’ current preferences, but how users’ preferences develop over time is still under-explored. In this work, we study the development of users’ musical preferences. Exploring musical preference consistency between short-term and long-term preferences in data from earlier studies, we find that users with higher musical expertise have more consistent preferences at their top-listened artists and tags than those with lower musical expertise. Users typically chose to explore genres that were close to their current preferences, and this effect was stronger for expert users. Based on these findings we conducted a user study on genre exploration to investigate (1) whether it is possible to nudge users to explore more distant genres, and (2) how users’ exploration behaviors within a genre are influenced by default recommendation settings that balance personalization with genre representativeness in different ways. Our results show that users were more likely to select the more distant genres if these were presented at the top of the list. However, users with high musical expertise were less likely to do so, consistent with our earlier findings. When given a representative or mixed (balanced) default for exploration within a genre, users selected less personalized recommendation settings and explored further away from their current preferences, than with a personalized default. However, this effect was moderated by users’ slider usage behaviors. Overall, our results suggest that (personalized) defaults can nudge users to explore new, more distant genres and songs. However, the effect is smaller for those with higher musical expertise levels.
Full text in ACM Digital Library
|
- LBRSoliciting User Preferences in Conversational Recommender Systems via Usage-related Questions
by Ivica Kostric (University of Stavanger, Norway), Krisztian Balog (University of Stavanger, Norway), and Filip Radlinski (Google, United Kingdom)
A key distinguishing feature of conversational recommender systems over traditional recommender systems is their ability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to ask questions directly about items or item attributes. These strategies do not perform well in cases where the user does not have sufficient knowledge of the target domain to answer such questions. Conversely, in a shopping setting, talking about the planned use of items does not present any difficulties, even for those that are new to a domain. In this paper, we propose a novel approach to preference elicitation by asking implicit questions based on item usage. Our approach consists of two main steps. First, we identify the sentences from a large review corpus that contain information about item usage. Then, we generate implicit preference elicitation questions from those sentences using a neural text-to-text model. The main contributions of this work also include a multi-stage data annotation protocol using crowdsourcing for collecting high-quality labeled training data for the neural model. We show that out approach is effective in selecting review sentences and transforming them to elicitation questions, even with limited training data.
Full text in ACM Digital Library
|
- LBRFR-FMSS: Federated Recommendation via Fake Marks and Secret Sharing
by Zhaohao Lin (Shenzhen University, China), Weike Pan (Shenzhen University, China), and Zhong Ming (Shenzhen University, China)
With the implementation of privacy protection laws such as GDPR, it is increasingly difficult for organizations to legally collect user data. However, a typical recommendation algorithm based on machine learning requires user data to learn user preferences. In order to protect user privacy, a lot of recent works turn to develop federated learning-based recommendation algorithms. However, some of these works can only protect the users’ rating values, some can only protect the users’ rating behavior (i.e., the engaged items), and only a few works can protect the both types of privacy at the same time. Moreover, most of them can only be applied to a specific algorithm or a class of similar algorithms. In this paper, we propose a generic cross-user federated recommendation framework called FR-FMSS. Our FR-FMSS can not only protect the two types of user privacy, but can also be applied to most recommendation algorithms for rating prediction, item ranking, and sequential recommendation. Specifically, we use fake marks and secret sharing to modify the data uploaded by the clients to the server, which protects user privacy without loss of model accuracy. We take three representative recommendation algorithms, i.e., MF-MPC, eALS, and Fossil, as examples to show how to apply our FR-FMSS to a specific algorithm.
Full text in ACM Digital Library
|
- LBRBaby Shark to Barracuda: Analyzing Children’s Music Listening Behavior
by Lawrence Spear (Boise State University, United States), Ashlee Milton (Boise State University, United States), Garrett Allen (Boise State University, United States), Amifa Raj (Boise State University, United States), Michael Green (Boise State University, United States), Michael D Ekstrand (Boise State University, United States), and Maria Soledad Pera (Boise State University, United States)
Music is an important part of childhood development, with online music listening platforms being a significant channel by which children consume music. Children’s offline music listening behavior has been heavily researched, yet relatively few studies explore how their behavior manifests online. In this paper, we use data from LastFM 1 Billion and the Spotify API to explore online music listening behavior of children, ages 6–17, using education levels as lenses for our analysis. Understanding the music listening behavior of children can be used to inform the future design of recommender systems.
Full text in ACM Digital Library
|
- LBRDo Users Appreciate Explanations of Recommendations? An Analysis in the Movie Domain
by Thi Ngoc Trang Tran (Institute of Software Technology, Graz University of Technology, Austria), Viet Man Le (Institute of Software Technology, Graz University of Technology, Austria), Muesluem Atas (Institute of Software Technology, Graz University of Technology, Austria), Alexander Felfernig (Institute of Software Technology, Graz University of Technology, Austria), Martin Stettinger (Institute of Software Technology, Graz University of Technology, Austria), and Andrei Popescu (Institute of Software Technology, Graz University of Technology, Austria)
In this paper, we provide insights into users’ needs regarding the inclusion of explanations in a movie recommender system. We have developed different variants of a movie recommender system prototype corresponding to different types of explanations and conducted an online user study to evaluate related explanations. The experimental results show that users do not always appreciate explanations. They want to see explanations when they are not satisfied with the recommended items. They expect to see explanations showing how well the recommended item meets their preferences. Moreover, explanation goals are interdependent and affect the overall satisfaction of users with the recommender system.
Full text in ACM Digital Library
|
- LBRAnalyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?
by Oleg Lesota (Johannes Kepler University and Linz Institute of Technology, Austria), Alessandro Melchiorre (Linz Institute of Technology, Austria), Navid Rekabsaz (Johannes Kepler University Linz and Linz Institute of Technology, Austria), Stefan Brandl (Johannes Kepler University Linz, Austria), Dominik Kowald (Graz University of Technology, Austria), Elisabeth Lex (Graz University of Technology, Austria), and Markus Schedl (Johannes Kepler University Linz and Linz Institute of Technology, Austria)
Several studies have identified discrepancies between the popularity of items in user profiles and the corresponding recommendation lists. Such behavior, which concerns a variety of recommendation algorithms, is referred to as popularity bias. Existing work predominantly adopts simple statistical measures, such as the difference of mean or median popularity, to quantify popularity bias. Moreover, it does so irrespective of user characteristics other than the inclination to popular content. In this work, in contrast, we propose to investigate popularity differences (between the user profile and recommendation list) in terms of median, a variety of statistical moments, as well as similarity measures that consider the entire popularity distributions (Kullback-Leibler divergence and Kendall’s τ rank-order correlation). This results in a more detailed picture of the characteristics of popularity bias. Furthermore, we investigate whether such algorithmic popularity bias affects users of different genders in the same way. We focus on music recommendation and conduct experiments on the recently released standardized LFM-2b dataset, containing listening profiles of Last.fm users. We investigate the algorithmic popularity bias of seven common recommendation algorithms (five collaborative filtering and two baselines). Our experiments show that (1) the studied metrics provide novel insights into popularity bias in comparison with only using average differences, (2) algorithms less inclined towards popularity bias amplification do not necessarily perform worse in terms of utility (NDCG), (3) the majority of the investigated recommenders intensify the popularity bias of the female users.
Full text in ACM Digital Library
|
- DSModeling Users and Items for Recommenders:There Is More than Semantics
by Mete Sertkan (E-Commerce TU Wien, Austria)
Recommender systems aim to help us to take better decisions and thus to save resources and increase satisfaction. Personalized recommendations are their main asset. In some domains, such as tourism or news, recommender systems rely more on content-based approaches to give personalized recommendations, due to domain-specific challenges. Content-based methods tend to recommend items semantically similar to the users’ previous consumptions. However, the content of items (e.g., text, visuals, categories, etc.) usually contains more than semantic properties.
In this PhD work we focus on the multifaceted nature of the recommendation items. Besides the mentioned semantic properties, we also take into account visual and textual style elements and more complex concepts such as emotions and personality. Our aim is to address people also on a non-rational, non-verbal, and rather emotional level; and thus, to improve recommendations. We propose a statistical-learning-based characterization of items, a picture-based approach to profile users and items, and a neural end-to-end approach, where we learn to represent users and items, and simultaneously to recommend. In all of the proposed methods we consider in addition to the semantic content either stylistic elements and/or more complex concepts like personality, and observe their impact. To contribute the community, we plan to open source our code and the datasets (to the extent our collaborators agree).
Full text in ACM Digital Library
|
- DSNeural Basket Embedding for Sequential Recommendation
by Vojtěch Vančura (Faculty of Information Technology Czech Technical University, Czech Republic)
Next basket prediction from historical purchases is quite a complex task, even for e-commerce datasets with a low number of items that are being purchased repeatedly. Neural approaches are not much better in predicting next purchases than simple heuristics. This paper focuses on the challenge of how to encode baskets into efficient neural embedding with low reconstruction error while maintaining the similarity of baskets in the latent space. In our representation, replacing a product with a similar product or increasing quantity will not change the embedding of the basket much. We believe that good basket representation is critical for subsequent prediction. Our analysis shows that state-of-the-art next basket prediction approaches have limitations in their representation of baskets. We would like to focus on this aspect in our future research.
Full text in ACM Digital Library
|
- INScaling Enterprise Recommender Systems for Decentralization
by Maurits van der Goes (The HEINEKEN Company, Netherlands)
Within decentralized organizations, the local demand for recommender systems to support business processes grows. The diversity in data sources and infrastructure challenges central engineering teams. Achieving a high delivery velocity without technical debt requires a scalable approach in the development and operations of recommender systems. At the HEINEKEN Company, we execute a machine learning operations method with five best practices: pipeline automation, data availability, exchangeable artifacts, observability, and policy-based security. Creating a culture of self-service, automation, and collaboration to scale recommender systems for decentralization. We demonstrate a practical use case of a self-service ML workspace deployment and a recommender system, that scale faster to subsidiaries and with less technical debt. This enables HEINEKEN to globally support applications that generate insights with local business impact.
Full text in ACM Digital Library
|
|
|
