%0 Conference Proceedings
%T Using Adjective Features from User Reviews to Generate Higher Quality and Explainable Recommendations
%+ National University of Singapore (NUS)
%A Xu, Xiaoying
%A Datta, Anindya
%A Dutta, Kaushik
%Z Track I: New Methods in Design Science Research
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B Working COnference on Shaping the Future of ICT Research
%C Tampa, FL, United States
%Y Anol Bhattacherjee
%Y Brian Fitzgerald
%I Springer
%3 Shaping the Future of ICT Research. Methods and Approaches
%V AICT-389
%P 18-34
%8 2012-12-13
%D 2012
%R 10.1007/978-3-642-35142-6_2
%K Recommender systems
%K User reviews
%K Adjective Features
%K Sparsity
%K Transparency
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X Recommender systems have played a significant role in alleviating the “information overload” problem. Existing Collaborative Filtering approaches face the data sparsity problem and transparency problem, and the content-based approaches suffer the problem of insufficient attributes. In this paper, we show that abundant adjective features embedded in user reviews can be used to characterize movies as well as users’ taste. We extend the standard TF-IDF term weighting scheme by introducing cluster frequency (CLF) to automatically extract high quality adjective features from user reviews for recommendation. We also develop a movie recommendation framework incorporating adjective features to generated highly accurate rating prediction and high quality recommendation explanation. The results of experiments performed on a real world dataset show that our proposed method outperforms the state-of-the-art techniques.
%G English
%Z TC 8
%Z WG 5.8
%2 https://inria.hal.science/hal-01515862/document
%2 https://inria.hal.science/hal-01515862/file/978-3-642-35142-6_2_Chapter.pdf
%L hal-01515862
%U https://inria.hal.science/hal-01515862
%~ SHS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC8
%~ IFIP-WG8-2
%~ IFIP-AICT-389