Effective LSTMs for Target-Dependent Sentiment Classification

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3298–3307, Osaka, Japan, December 11-17 2016. Effective LSTMs for Target-Dependent Sentiment Classification Duyu Tang, Bing Qin, Xiaocheng Feng, Ting Liu Harbin Institute of Technology, Harbin, China {dytang, qinb, xcfeng, tliu}@ir.hit.edu.cn Abstract Target-dependent sentiment classification remains a challenge: modeling the semantic related- ness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a sentence towards the target. Therefore, it is desirable to integrate the connections between target word and context words when building a learning system. In this paper, we develop two target dependent long short-term memory (LSTM) models, where target information is automatically taken into account. We evaluate our methods on a benchmark dataset from Twitter. Empirical results show that modeling sentence represen- tation with standard LSTM does not perform well. Incorporating target information into LSTM can significantly boost the classification accuracy. The target-dependent LSTM models achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.1 1 Introduction Sentiment analysis, also known as opinion mining (Pang and Lee, 2008; Liu, 2012), is a fundamental task in natural language processing and computational linguistics. Sentiment analysis is crucial to un- derstanding user generated text in social networks or product reviews, and has drawn a lot of attentions from both industry and academic communities. In this paper, we focus on target-dependent sentiment classification (Jiang et al., 2011; Dong et al., 2014; Vo and Zhang, 2015), which is a fundamental and extensively studied task in the field of sentiment analysis. Given a sentence and a target mention, the task calls for inferring the sentiment polarity (e.g. positive, negative, neutral) of the sentence towards the target. For example, let us consider the sentence: “I bought a new camera. The picture quality is amazing but the battery life is too short”. If the target string is picture quality, the expected sentiment polarity is “positive” as the sentence expresses a positive opinion towards picture quality. If we consider the target as battery life, the correct sentiment polarity should be “negative”. Target-dependent sentiment classification is typically regarded as a kind of text classification problem in literature. Majority of existing studies build sentiment classifiers with supervised machine learning approach, such as feature based Supported Vector Machine (Jiang et al., 2011) or neural network ap- proaches (Dong et al., 2014; Vo and Zhang, 2015). Despite the effectiveness of these approaches, we argue that target-dependent sentiment classification remains a challenge: how to effectively model the semantic relatedness of a target word with its context words in a sentence. One straight forward way to address this problem is to manually design a set of target-dependent features, and integrate them into existing feature-based SVM. However, feature engineering is labor intensive and the “sparse” and “dis- crete” features are clumsy in encoding side information like target-context relatedness. In addition, a person asked to do this task will naturally “look at” parts of relevant context words which …

Content truncated to 500 words