Context-Aware User and Item Representations Based on Unsupervised Context Extraction From Reviews

IEEE Access

Saranya Maneeroj¹  Atsuhiro Takasu²  Padipat Sitkrongwong³ 

[1] Department of Mathematics and Computer Science, Faculty of Science, Advanced Virtual and Intelligent Computing Center, Chulalongkorn University, Bangkok, Thailand;National Institute of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan;The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan;

关键词: Attention mechanism;    context-aware recommender systems;    region embedding;    representation learning;   

DOI  :  10.1109/ACCESS.2020.2993063

来源: DOAJ

【 摘 要 】

User reviews often supply valuable information to alleviate the rating sparsity problem that can occur in recommender systems. Recent work has employed deep learning techniques to learn user and item representations from reviews, which are then used to predict ratings. Such representations are usually learned by considering every word in previous reviews, including words that are irrelevant to user preferences or item features. Some approaches try to identify and extract significant words from reviews based on a predefined list of contexts, where contexts such as the season or weather could have strong influences on user decisions about items, and which are more relevant to their preferences or sought-after features. Specifying optimal values for contexts, however, is not a trivial task and the values are mostly restricted to a single word format. To overcome these limitations, we propose a novel unsupervised method for extracting contexts from reviews, which are then utilized to construct user and item representations. To this end, we adopt a region embedding technique to automatically extract a context as any word in a text region that influences patterns of rating distributions in reviews. Instead of considering every word in all previous reviews, our user and item representations are dynamically constructed based on different relevance levels among the extracted contexts from a particular review by applying our interaction and attention modules. Experiments demonstrated that utilizing our representations for rating prediction could outperform existing state-of-the-art context-aware and review-based recommendation techniques.

【 授权许可】

Unknown