Aspect-level Sentiment Classification with Reinforcement Learning

Tingting Wang, Jie Zhou, Qinmin Vivian Hu, Liang He

Abstract: Aspect-level sentiment classification aims to predict the sentiment polarity of a given aspect in a sentence. However, most of the existing methods focus on the information of the entire sentence rather than a segment that describes the aspect, making it difficult to identify the mapping between an aspect and a segment. Moreover, these methods are prone to the noise in the sentence. To alleviate this problem, we propose a novel approach that models the specific segments for aspect-level sentiment classification in a reinforcement learning framework. Our approach consists of two parts: an aspect segment extraction (ASE) model and an aspect sentiment classification (ASC) model. Specifically, the ASE model extracts the corresponding segment with reinforcement learning and feeds the extracted segment into the ASC model. Then, the ASC model makes the segment-level prediction and provides rewards to the ASE model. The experimental results indicate that our proposed approach can extract the segment towards the aspect effectively, and thus obtains competitive performance. Furthermore, we provide an intuitive understanding of why our ASE model is more effective for aspect-level sentiment classification via case studies.