Advertisement

Effective Comment Sentence Recognition for Feature-Based Opinion Mining

  • Hui Song
  • Botian Yang
  • Xiaoqiang Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8346)

Abstract

Feature-based opinion mining aims to extract fine-grained comments in product features level from the product reviews. Previous work proposed a lot of statistics-based and model-based approaches. However, the extraction result is not satisfying when these methods are actually used into an application with large useless data due to the complexity of Chinese. Through analyzing the samples hadn’t been extracted correctly, we found some extracting patterns or models have been misused on the useless sentences which lead to wrong extraction. This paper focuses on improving the POS-pattern match methodology. The core idea of our approach is picking out the effective comment sentences before feature and sentiment extraction based on neural network training. Three attributes of sentences are selected to learn the classification algorithm. Experiment gives the superior parameters of the algorithm. We report the classification performance and also compare the feature extraction performance with classification process and not. The result on practical data set demonstrates the effect of this approach.

Keywords

POS-Pattern Effective Comment Sentence Neural Network Products Review 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2004, pp. 168–177. ACM (2004)Google Scholar
  2. 2.
    Turney, P.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proc of ACL, pp. 417–424. ACM, New York (2002)Google Scholar
  3. 3.
    Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: Proceedings of the International Conference on Web Search and Web Data Mining, WSDM 2008, pp. 231–240. ACM (2008)Google Scholar
  4. 4.
    Jin, W., Ho, H., Srihari, R.: Opinion Miner: a novel machine learning system for web opinion mining and extraction. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1195–1204. ACM (2009)Google Scholar
  5. 5.
    Qi, L., Chen, L.: Comparison of Model-Based Learning Methods for Feature-Level Opinion Mining. In: Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, WI-IAT 2011, vol. 01, pp. 265–273 (2011)Google Scholar
  6. 6.
    Su, J., Zhang, B., Xu, X.: Advances in Machine Learning Based Text Categorization. Journal of Software, 1848–1859 (2006) (in Chinese)Google Scholar
  7. 7.
    Baccianella, S., Esuli, A., Sebastiani, F.: Multi-facet Rating of Product Reviews. In: Boughanem, M., Berrut, C., Mothe, J., Soule-Dupuy, C. (eds.) ECIR 2009. LNCS, vol. 5478, pp. 461–472. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  8. 8.
    Dong (Haoyuan), L., Anne, L., Pascal, P., Mathieu, R.: Extraction of Unexpected Sentences: A Sentiment Classification Assessed Approach. J. Intelligent Data Analysis 14, 31–46 (2010)Google Scholar
  9. 9.
    Popescu, A., Etzioni, O.: Extracting product features and opinions from reviews. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 339–346. Association for Computational Linguistics (2005)Google Scholar
  10. 10.
    Zhang, H., Yu, Z., Xu, M., Shi, Y.: Feature-level sentiment analysis for Chinese product reviews. In: 3rd International Conference on Computer Research and Development, Shanghai, pp. 135–140 (2011)Google Scholar
  11. 11.
    Zhang, L., Lim, S.H., Liu, B., O’Brien-Strain, E.: Extracting and Ranking Product Features in Opinion Documents. In: Proceedings of COLING (2010)Google Scholar
  12. 12.
    Lin, Z., Tan, S., Cheng, X.: Sentiment Classification Analysis Based on Extraction of Sentiment Key Sentence. Journal of Computer Research and Development 49(11), 2376–2382 (2012) (in Chinese)Google Scholar
  13. 13.
    Zhai, Z., Liu, B., Zhang, L., Xu, H., Jia, P.: Identifying Evaluative Sentences in Online Discussions. In: The Twenty-Fifth AAAI Conference on Artificial Intelligence, pp. 933–938 (2011)Google Scholar
  14. 14.
    Song, H., Fan, Y., Liu, X.: Frequent Pattern Learning Based Feature-level Opinion Mining on Online Consumer Reviews. Advances in Information Sciences and Service Sciences 11(4), 133–141 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Hui Song
    • 1
  • Botian Yang
    • 1
  • Xiaoqiang Liu
    • 1
  1. 1.College of Computer Science and TechnologyDonghua UniversityShanghaiChina

Personalised recommendations