Combining text summarization and aspect-based sentiment analysis of users' reviews to justify recommendations

In this paper we present a methodology to justify recommendations that relies on the information extracted from users' reviews discussing the available items. The intuition behind the approach is to conceive the justification as a summary of the most relevant and distinguishing aspects of the item, automatically obtained by analyzing its reviews. To this end, we designed a pipeline of natural language processing techniques including aspect extraction, sentiment analysis and text summarization to gather the reviews, process the relevant excerpts, and generate a unique synthesis presenting the main characteristics of the item. Such a summary is finally presented to the target user as a justification of the received recommendation. In the experimental evaluation we carried out a user study in the movie domain (N=141) and the results showed that our approach is able to make the recommendation process more transparent, engaging and trustful for the users.

[1]  Pasquale Lops,et al.  ExpLOD: A Framework for Explaining Recommendations based on the Linked Open Data Cloud , 2016, RecSys.

[2]  Tao Chen,et al.  TriRank: Review-aware Explainable Recommendation by Modeling Aspects , 2015, CIKM.

[3]  Giovanni Semeraro,et al.  Centroid-based Text Summarization through Compositionality of Word Embeddings , 2017, MultiLing@EACL.

[4]  Taher H. Haveliwala.  Topic-Sensitive PageRank: A Context-Sensitive Ranking Algorithm for Web Search , 2003, IEEE Trans. Knowl. Data Eng..

[5]  Li Chen,et al.  Augmenting service recommender systems by incorporating contextual opinions from user reviews , 2015, User Modeling and User-Adapted Interaction.

[6]  Lei Zhang,et al.  A Survey of Opinion Mining and Sentiment Analysis , 2012, Mining Text Data.

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Zheng Xiao-lin Wu Ya-feng Chen De-ren Hu Zhong-kai.  Product recommendation algorithm based on users’ reviews mining , 2013 .

[9]  Pasquale Lops,et al.  Justifying Recommendations through Aspect-based Sentiment Analysis of Users Reviews , 2019, UMAP.

[10]  Barry Smyth,et al.  A Live-User Study of Opinionated Explanations for Recommender Systems , 2016, IUI.

[11]  Pasquale Lops,et al.  Linked open data-based explanations for transparent recommender systems , 2019, Int. J. Hum. Comput. Stud..

[12]  F. Maxwell Harper,et al.  Crowd-Based Personalized Natural Language Explanations for Recommendations , 2016, RecSys.

[13]  Jorge A. Balazs,et al.  Opinion Mining and Information Fusion: A survey , 2016, Inf. Fusion.

[14]  Dragomir R. Radev,et al.  Centroid-based summarization of multiple documents , 2004, Inf. Process. Manag..

[15]  D VelásquezJuan,et al.  Opinion Mining and Information Fusion , 2016 .

[16]  Or Biran,et al.  Explanation and Justification in Machine Learning : A Survey Or , 2017 .

[17]  Nava Tintarev,et al.  Evaluating the effectiveness of explanations for recommender systems , 2012, User Modeling and User-Adapted Interaction.

[18]  Pasquale Lops,et al.  A Multi-criteria Recommender System Exploiting Aspect-based Sentiment Analysis of Users' Reviews , 2017, RecSys.