Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 325–335, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization Bishan Yang Department of Computer Science Cornell University bishan@cs.cornell.edu Claire Cardie Department of Computer Science Cornell University cardie@cs.cornell.edu Abstract This paper proposes a novel context-aware method for analyzing sentiment at the level of individual sentences. Most ex- isting machine learning approaches suf- fer from limitations in the modeling of complex linguistic structures across sen- tences and often fail to capture non- local contextual cues that are important for sentiment interpretation. In contrast, our approach allows structured modeling of sentiment while taking into account both local and global contextual infor- mation. Specifically, we encode intu- itive lexical and discourse knowledge as expressive constraints and integrate them into the learning of conditional random field models via posterior regularization. The context-aware constraints provide ad- ditional power to the CRF model and can guide semi-supervised learning when la- beled data is limited. Experiments on standard product review datasets show that our method outperforms the state-of-the- art methods in both the supervised and semi-supervised settings. 1 Introduction The ability to extract sentiment from text is cru- cial for many opinion-mining applications such as opinion summarization, opinion question answer- ing and opinion retrieval. Accordingly, extract- ing sentiment at the fine-grained level (e.g. at the sentence- or phrase-level) has received increasing attention recently due to its challenging nature and its importance in supporting these opinion analysis tasks (Pang and Lee, 2008). In this paper, we focus on the task of sentence- level sentiment classification in online reviews. Typical approaches to the task employ supervised machine learning algorithms with rich features and take into account the interactions between words to handle compositional effects such as po- larity reversal (e.g. (Nakagawa et al., 2010; Socher et al., 2013)). Still, their methods can en- counter difficulty when the sentence on its own does not contain strong enough sentiment signals (due to the lack of statistical evidence or the re- quirement for background knowledge). Consider the following review for example, 1. Hearing the music in real stereo is a true reve- lation. 2. You can feel that the music is no longer constrained by the mono recording. 3. In fact, it is more like the players are performing on a stage in front of you ... Existing feature-based classifiers may be effective in identifying the positive sentiment of the first sentence due to the use of the word revelation, but they could be less effective in the last two sen- tences due to the lack of explicit sentiment signals. However, if we examine these sentences within the discourse context, we can see that: the second sen- tence expresses sentiment towards the same aspect – the music – as the first sentence; the third sen- tence expands the second sentence with the dis- course connective In fact. These discourse-level relations help indicate that sentence 2 and 3 are …

Content truncated to 500 words