Learning Semantic Representations of Users and Products for Document Level Sentiment Classification

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 1014–1023, Beijing, China, July 26-31, 2015. c⃝2015 Association for Computational Linguistics Learning Semantic Representations of Users and Products for Document Level Sentiment Classification Duyu Tang, Bing Qin∗, Ting Liu Harbin Institute of Technology, Harbin, China {dytang, qinb, tliu}@ir.hit.edu.cn Abstract Neural network methods have achieved promising results for sentiment classifica- tion of text. However, these models on- ly use semantics of texts, while ignoring users who express the sentiment and prod- ucts which are evaluated, both of which have great influences on interpreting the sentiment of text. In this paper, we ad- dress this issue by incorporating user- and product- level information into a neural network approach for document level sen- timent classification. Users and product- s are modeled using vector space mod- els, the representations of which capture important global clues such as individu- al preferences of users or overall quali- ties of products. Such global evidence in turn facilitates embedding learning pro- cedure at document level, yielding better text representations. By combining ev- idence at user-, product- and document- level in a unified neural framework, the proposed model achieves state-of-the-art performances on IMDB and Yelp dataset- s1. 1 Introduction Document-level sentiment classification is a fun- damental problem in the field of sentiment analy- sis and opinion mining (Pang and Lee, 2008; Liu, 2012). The task is to infer the sentiment polari- ty or intensity (e.g. 1-5 or 1-10 stars on review sites) of a document. Dominating studies follow Pang et al. (2002; 2005) and regard this problem as a multi-class classification task. They usually ∗Corresponding author. 1The codes and datasets are available at http://ir. hit.edu.cn/˜dytang/ use machine learning algorithms, and build sen- timent classifier from documents with accompa- nying sentiment labels. Since the performance of a machine learner is heavily dependent on the choice of data representations (Domingos, 2012), many works focus on designing effective features (Pang et al., 2002; Qu et al., 2010; Kiritchenko et al., 2014) or learning discriminative features from data with neural networks (Socher et al., 2013; Kalchbrenner et al., 2014; Le and Mikolov, 2014). Despite the apparent success of neural network methods, they typically only use text information while ignoring the important influences of users and products. Let us take reviews with respect to 1-5 rating scales as an example. A critical user might write a review “it works great” and mark 4 stars, while a lenient user might give 5 stars even if he posts an (almost) identical review. In this case, user preference affects the sentiment rating of a re- view. Product quality also has an impact on review sentiment rating. Reviews towards high-quality products (e.g. Macbook) tend to receive higher ratings than those towards low-quality products. Therefore, it is feasible to leverage individual pref- erences of users and overall qualities of products to build a smarter sentiment classifier and achieve better performance2. In this paper, we propose a …

Content truncated to 500 words