Paper Session 11: Semantics and Sentiment

Date: Wednesday, Aug 30, 2017, 14:00-15:00
Location: Room 1
Chair: Boi Faltings

  • SPA Semantic-Aware Profile Updating Model for Text Recommendation by Hossein Rahmatizadeh Zagheli, Hamed Zamani and Azadeh Shakery

    Content-based recommender systems (CBRSs) rely on user-item similarities that are calculated between user profiles and item representations. Appropriate representations for each user profile based on the user’s past preferences can result in a great impact on user’s satisfaction in CBRSs. In this paper, we focus on text recommendation and propose a novel profile updating model based on previously recommended items as well as semantic similarity of terms calculated using distributed representation of words. We evaluate our models using two standard text recommendation datasets: TREC-9 Filtering Track and CLEF 2008-09 INFILE Track collections. Our experiments investigate the importance of both past recommended items and semantic similarities in recommendation performance. The proposed profile updating method significantly outperforms the baselines, which indicates the importance of incorporating semantic similarities in the profile updating task.

  • SPA Multi-criteria Recommender System Exploiting Aspect-based Sentiment Analysis of Users’ Reviews by Cataldo Musto, Marco De Gemmis, Giovanni Semeraro and Pasquale Lops

    In this paper we propose a multi-criteria recommender system based on collaborative filtering (CF) techniques, which exploits the information conveyed by users’ reviews to provide a multi-faceted representation of users’ interests.

    To this end, we exploited a framework for opinion mining and sentiment analysis, which automatically extracts relevant aspects and sentiment scores from users’ reviews. As an example, in a restaurant recommendation scenario, the aspects may regard food quality, service, position, atmosphere of the place and so on.

    Such a multi-faceted representation of the user is used to feed a multi-criteria CF algorithm which predicts user interest in a particular item and provides her with recommendations.

    In the experimental session we evaluated the performance of the algorithm against several state-of-the-art baselines; Results confirmed the insight behind this work, since our approach was able to overcome both single-criteria recommendation algorithms as well as more sophisticated techniques based on matrix factorization.

  • SPExploring the Semantic Gap for Movie Recommendations by Mehdi Elahi, Yashar Deldjoo, Farshad Bakhshandegan, Leonardo Cella, Stefano Cereda and Paolo Cremonesi

    In the last years, we have seen much attention given to the semantic gap problem in multimedia recommender systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it.

    In this paper, we explore a different point of view, by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendations that extract low-level mise-en-scene features from multimedia content and combine it with high-level features provided by the wisdom of the crowd.

    For our purposes, we first designed an empirical study involving 100 subjects and implemented a movie recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a combination of mise-en-scene features and movie attributes. We collected data regarding the quality perceived by the users. In another study, we compared users’ perceived utility of recommendation with offline quality measures.

    Results from both studies show that the introduction of mise-en-scene features in conjunction with traditional attributes improves both offline and online quality of recommendations.

  • SPDynamic Scholarly Collaborator Recommendation via Competitive Multi-Agent Reinforcement Learning by Yang Zhang, Chenwei Zhang and Xiaozhong Liu

    In an interdisciplinary environment, scientific collaboration is becoming increasingly important. Helping scholars make a right choice of potential collaborators is essential in achieving scientific success. Intuitively, the generation of collaboration relationship is a dynamic process. For instance, one scholar may first choose to work with Scholar A, and then work with Scholar B after accumulating additional academic credits. To address this property, we propose a novel dynamic collaboration recommendation method by adapting the multi-agent reinforcement learning technique to the coauthor network analysis. The collaborator selection is optimized from several different scholar similarity measurements. Unlike prior studies, the proposed method characterizes scholarly competition, a.k.a. different scholars will compete for potential collaborator at each iteration. An evaluation with the ACM data shows that multi-agent reinforcement learning plus scholarly competition modeling can be significant for collaboration recommendation.

Back to Program

Diamond Supporter
Platinum Supporters
Gold Supporter
Silver Supporter
Special Supporters