ABSTRACT
The popularity of Web 2.0 has resulted in a large number of publicly available online consumer reviews created by a demographically diverse user base. Information about the authors of these reviews, such as age, gender and location, provided by many on-line consumer review platforms may allow companies to better understand the preferences of different market segments and improve their product design, manufacturing processes and marketing campaigns accordingly. However, previous work in sentiment analysis has largely ignored these additional user meta-data. To address this deficiency, in this paper, we propose parametric and non-parametric User-aware Sentiment Topic Models (USTM) that incorporate demographic information of review authors into topic modeling process in order to discover associations between market segments, topical aspects and sentiments. Qualitative examination of the topics discovered using USTM framework in the two datasets collected from popular online consumer review platforms as well as quantitative evaluation of the methods utilizing those topics for the tasks of review sentiment classification and user attribute prediction both indicate the utility of accounting for demographic information of review authors in opinion mining.
- D. M. Blei, T. L. Griffiths, and M. I. Jordan. The Nested Chinese Restaurant Process and Bayesian Nonparametric Inference of Topic Hierarchies. JACM, 57(7), 2010. Google ScholarDigital Library
- D. M. Blei and J. D. McAuliffe. Supervised Topic Models. In Proceedings of the 20th NIPS, pages 121--128, 2007.Google Scholar
- D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Learning Research, 3:993--1022, 2003. Google ScholarDigital Library
- W. Gao, N. Yoshinaga, N. Kaji, and M. Kitsuregawa. Modeling User Leniency and Product Popularity for Sentiment Classification. In Proceedings of the 6th IJCNLP, pages 1107--1111, 2013.Google Scholar
- T. Hofmann. Probabilistic Latent Semantic Indexing. In Proceedings of the 22nd SIGIR, pages 50--57, 1999. Google ScholarDigital Library
- M. Hu and B. Liu. Mining and Summarizing Customer Reviews. In Proceedings of the 10th ACM SIGKDD, pages 168--177, 2004. Google ScholarDigital Library
- N. Jakob and I. Gurevych. Extracting Opinion Targets in a Single- and Cross-domain Setting with Conditional Random Fields. In Proceedings of the 2010 EMNLP, pages 1035--1045, 2010. Google ScholarDigital Library
- Y. Jo and A. H. Oh. Aspect and Sentiment Unification Model for Online Review Analysis. In Proceedings of the 4th WSDM, pages 815--824, 2011. Google ScholarDigital Library
- J. H. Kim, D. Kim, S. Kim, and A. Oh. Modeling Topic Hierarchies with the Recursive Chinese Restaurant Process. In Proceedings of the 21st ACM CIKM, pages 783--792, 2012. Google ScholarDigital Library
- S. Kim, J. Zhang, Z. Chen, A. H. Oh, and S. Liu. A Hierarchical Aspect-Sentiment Model for Online Reviews. In Proceedings of the 27th AAAI, pages 526--533, 2013.Google Scholar
- A. Kotov and E. Agichtein. The Importance of Being Socially-Savvy: Quantifying the Influence of Social Networks on Microblog Retrieval. In Proceedings of the 22nd CIKM, pages 1905--1908, 2013. Google ScholarDigital Library
- A. Kotov, V. Rakesh, E. Agichtein, and C. K. Reddy. Geographical Latent Variable Models for Microblog Retrieval. In Proceedings of the 37th ECIR, pages 635--647, 2015.Google ScholarCross Ref
- A. Kotov, Y. Wang, and E. Agichtein. Leveraging Geographical Metadata to Improve Search over Social Media. In Proceedings of the 22nd WWW, pages 151--152, 2013. Google ScholarDigital Library
- H. Lakkaraju, C. Bhattacharyya, I. Bhattacharya, and S. Merugu. Exploiting Coherence for the Simultaneous Discovery of Latent Facets and associated Sentiments. In Proceedings of the 11th SDM, pages 498--509, 2011.Google ScholarCross Ref
- F. Li, C. Han, M. Huang, X. Zhu, Y.-J. Xia, S. Zhang, and H. Yu. Structure-aware Review Mining and Summarization. In Proceedings of the 23rd COLING, pages 653--661, 2010. Google ScholarDigital Library
- F. Li, S. Wang, S. Liu, and M. Zhang. SUIT: A Supervised User-Item Based Topic Model for Sentiment Analysis. In Proceedings of the 28th AAAI, pages 1636--1642, 2014.Google Scholar
- C. Lin and Y. He. Joint Sentiment/Topic Model for Sentiment Analysis. In Proceedings of the 18th CIKM, pages 375--384, 2009. Google ScholarDigital Library
- C. Lin, Y. He, R. Everson, and S. Ruger. Weakly Supervised Joint Sentiment-Topic Detection from Text. IEEE Transactions on Knowledge and Data Engineering, 24(6):1134--1145, 2012. Google ScholarDigital Library
- T. Ma and X. Wan. Opinion Target Extraction in Chinese News Comments. In Proceedings of the 23rd COLING, pages 782--790, 2010. Google ScholarDigital Library
- Q. Mei, X. Ling, M. Wondra, H. Su, and C. Zhai. Topic Sentiment Mixture: Modeling Facets and Opinions in Weblogs. In Proceedings of the 16th WWW, pages 171--180, 2007. Google ScholarDigital Library
- S. Moghaddam and M. Ester. ILDA: Interdependent LDA Model for Learning Latent Aspects and Their Ratings from Online Product Reviews. In Proceedings of the 34th SIGIR, pages 665--674, 2011. Google ScholarDigital Library
- A. Mukherjee and B. Liu. Aspect Extraction Through Semi-supervised Modeling. In Proceedings of the 50th ACL, pages 339--348, 2012. Google ScholarDigital Library
- A.-M. Popescu and O. Etzioni. Extracting Product Features and Opinions from Reviews. In Proceedings of the 2005 EMNLP-HLT, pages 339--346, 2005. Google ScholarDigital Library
- D. Ramage, C. D. Manning, and S. Dumais. Partially Labeled Topic Models for Interpretable Text Mining. In Proceedings of the 17th SIGKDD, pages 457--465, 2011. Google ScholarDigital Library
- C. Sauper, A. Haghighi, and R. Barzilay. Content Models with Attitude. In Proceedings of the 49th ACL-HLT, pages 350--358, 2011. Google ScholarDigital Library
- C. Tan, L. Lee, J. Tang, L. Jiang, M. Zhou, and P. Li. User-level Sentiment Analysis Incorporating Social Networks. In Proceedings of the 17th ACM SIGKDD, pages 1397--1405, 2011. Google ScholarDigital Library
- I. Titov and R. Mcdonald. A Joint Model of Text and Aspect Ratings for Sentiment Summarization. In Proceedings of 46th ACL-HLT, pages 308--316, 2008.Google Scholar
- I. Titov and R. McDonald. Modeling Online Reviews with Multi-grain Topic Models. In Proceedings of the 17th WWW, pages 111--120, 2008. Google ScholarDigital Library
- P. D. Turney and M. L. Littman. Measuring Praise and Criticism: Inference of Semantic Orientation from Association. ACM TOIS, 21(4):315--346, 2003. Google ScholarDigital Library
- H. Wang, Y. Lu, and C. Zhai. Latent Aspect Rating Analysis on Review Text Data: A Rating Regression Approach. In Proceedings of the 16th SIGKDD, pages 783--792, 2010. Google ScholarDigital Library
- T. Zhao, C. Li, Q. Ding, and L. Li. User-sentiment Topic Model: Refining User's Topics with Sentiment Information. In Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics, 2012. Google ScholarDigital Library
Index Terms
- Parametric and Non-parametric User-aware Sentiment Topic Models
Recommendations
Modeling online reviews with multi-grain topic models
WWW '08: Proceedings of the 17th international conference on World Wide WebIn this paper we present a novel framework for extracting the ratable aspects of objects from online user reviews. Extracting such aspects is an important challenge in automatically mining product opinions from the web and in generating opinion-based ...
Joint sentiment/topic model for sentiment analysis
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementSentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework based on Latent Dirichlet ...
Topic sentiment change analysis
MLDM'11: Proceedings of the 7th international conference on Machine learning and data mining in pattern recognitionPublic opinions on a topic may change over time. Topic Sentiment change analysis is a new research problem consisting of two main components: (a) mining opinions on a certain topic, and (b) detect significant changes of sentiment of the opinions on the ...
Comments