Incorporating Multi-Level User Preference into Document-Level Sentiment Classification

• DOI: 10.1145/3234512
• Publication Date: 2018-11-20T14:19:23Z
• Authors: Junjie Li; Haoran Li; Xiaomian Kang; Haitong Yang; Chengqing Zong
• Keywords: Sentiment Analysis; Polarity (international relations)

Document-level sentiment classification aims to predict a user’s polarity in document about product. Most existing methods only focus on review contents and ignore users who post reviews. In fact, when reviewing product, different have word-using habits express opinions (i.e., word-level user preference), care attributes of the product aspect-level characteristics score polarity-level preference). These preferences great influence interpreting text. To address this issue, we propose model called Hierarchical User Attention Network (HUAN), which incorporates multi-level preference into hierarchical neural network perform document-level classification. Specifically, HUAN encodes kinds information (word, sentence, aspect, document) structure imports embedding attention mechanism these preferences. Empirical results two real-world datasets show that achieves state-of-the-art performance. Furthermore, can also mine important products for users.