A bipartite graph model for implicit feature extraction in Chinese reviews

With the increasing number of network comments, mining product reviews is an emerging area of research which fundamental work is focused on feature extraction. Previous studies mainly focus on explicit features extraction while often ignore implicit features which haven't been stated clearly but containing necessary information for analyzing comments. Actually in our study, we find a lot of implicit features in the comments, so how to quickly and accurately mine features from web reviews for potential customers and business has important significance. In this paper, explicit features and “feature-opinion” pairs in the explicit sentences are extracted by Conditional Random Field and implicit product features are recognized by a bipartite graph model based on random walk algorithm. The experiment results demonstrate that these two methods we proposed can improve the accuracy of feature and collocation extraction against state-of-the-art techniques.

[1]  Michael Gertz,et al.  Reverse engineering for Web data: from visual to semantic structures , 2002, Proceedings 18th International Conference on Data Engineering.

[2]  Hongfei Yan,et al.  Comparing Twitter and Traditional Media Using Topic Models , 2011, ECIR.

[3]  Yue Wang,et al.  An Exploration of Tie-Breaking for Microblog Retrieval , 2014, ECIR.

[4]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[5]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[6]  Nina Wacholder,et al.  Identifying Sarcasm in Twitter: A Closer Look , 2011, ACL.

[7]  Philip S. Yu,et al.  A holistic lexicon-based approach to opinion mining , 2008, WSDM '08.

[8]  Zhen Hai,et al.  Implicit Feature Identification via Co-occurrence Association Rule Mining , 2011, CICLing.

[9]  Paolo Rosso,et al.  A multidimensional approach for detecting irony in Twitter , 2013, Lang. Resour. Evaluation.

[10]  Zhijun Yan,et al.  An Lda and Synonym Lexicon Based Approach to Product Feature Extraction from Online Consumer Product Reviews , 2013 .

[11]  Conrad S. Tucker,et al.  A Product Feature Inference Model for Mining Implicit Customer Preferences Within Large Scale Social Media Networks , 2015 .

[12]  Kentaro Inui,et al.  Collecting Evaluative Expressions for Opinion Extraction , 2004, IJCNLP.

[13]  Zhendong Niu,et al.  Fine-grained Product Features Extraction and Categorization in Reviews Opinion Mining , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[14]  Iryna Gurevych,et al.  Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields , 2010, EMNLP.

[15]  Conrad S. Tucker,et al.  Automated Discovery of Lead Users and Latent Product Features by Mining Large Scale Social Media Networks , 2015 .

[16]  Xu Ling,et al.  Topic sentiment mixture: modeling facets and opinions in weblogs , 2007, WWW '07.

[17]  Hua Xu,et al.  Clustering product features for opinion mining , 2011, WSDM '11.

[18]  Shiwen Yu,et al.  Using Pointwise Mutual Information to Identify Implicit Features in Customer Reviews , 2006, ICCPOL.

[19]  Harry Shum,et al.  Twitter Topic Summarization by Ranking Tweets using Social Influence and Content Quality , 2012, COLING.