Product Feature Mining: Semantic Clues versus Syntactic Constituents

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 336–346, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics Product Feature Mining: Semantic Clues versus Syntactic Constituents Liheng Xu, Kang Liu, Siwei Lai and Jun Zhao National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China {lhxu, kliu, swlai, jzhao}@nlpr.ia.ac.cn Abstract Product feature mining is a key subtask in fine-grained opinion mining. Previ- ous works often use syntax constituents in this task. However, syntax-based methods can only use discrete contextual informa- tion, which may suffer from data sparsity. This paper proposes a novel product fea- ture mining method which leverages lexi- cal and contextual semantic clues. Lexical semantic clue verifies whether a candidate term is related to the target product, and contextual semantic clue serves as a soft pattern miner to find candidates, which ex- ploits semantics of each word in context so as to alleviate the data sparsity prob- lem. We build a semantic similarity graph to encode lexical semantic clue, and em- ploy a convolutional neural model to cap- ture contextual semantic clue. Then Label Propagation is applied to combine both se- mantic clues. Experimental results show that our semantics-based method signif- icantly outperforms conventional syntax- based approaches, which not only mines product features more accurately, but also extracts more infrequent product features. 1 Introduction In recent years, opinion mining has helped cus- tomers a lot to make informed purchase decisions. However, with the rapid growth of e-commerce, customers are no longer satisfied with the over- all opinion ratings provided by traditional senti- ment analysis systems. The detailed functions or attributes of products, which are called product features, receive more attention. Nevertheless, a product may have thousands of features, which makes it impractical for a customer to investigate them all. Therefore, mining product features au- tomatically from online reviews is shown to be a key step for opinion summarization (Hu and Liu, 2004; Qiu et al., 2009) and fine-grained sentiment analysis (Jiang et al., 2011; Li et al., 2012). Previous works often mine product features via syntactic constituent matching (Popescu and Et- zioni, 2005; Qiu et al., 2009; Zhang et al., 2010). The basic idea is that reviewers tend to comment on product features in similar syntactic structures. Therefore, it is natural to mine product features by using syntactic patterns. For example, in Figure 1, the upper box shows a dependency tree produced by Stanford Parser (de Marneffe et al., 2006), and the lower box shows a common syntactic pattern from (Zhang et al., 2010), where <feature/NN> is a wildcard to be fit in reviews and NN denotes the required POS tag of the wildcard. Usually, the product name mp3 is specified, and when screen matches the wildcard, it is likely to be a product feature of mp3. Figure 1: An example of syntax-based prod- uct feature mining procedure. The word screen matches the wildcard <feature/NN>. Therefore, screen is likely to be a product feature of mp3. …

Content truncated to 500 words