Product Feature Extraction via Topic Model and Synonym Recognition Approach
Abstract
As e-commerce is becoming more and more popular, sentiment analysis of online reviews has become one of the most important studies in text mining. The main task of sentiment analysis is to analyze the user’s attitude towards different product features. Product feature extraction refers to extracting the product features of user evaluation from reviews, which is the first step to achieve further sentiment analysis tasks. The existing product feature extraction methods do not address flexibility and randomness of online reviews. Moreover, these methods have defects such as low accuracy and recall rate. In this study, we propose a product feature extraction method based on topic model and synonym recognition. Firstly, we set a threshold that TF-IDF value of a product feature noun must reach to filter meaningless words in reviews, and select the threshold by grid search. Secondly, considering the occurrence rule of different product features in reviews, we propose a novel product similarity calculation, which also performs weighted fusion based on information entropy with a variety of general similarity calculation methods. Finally, compared with traditional methods, the experimental results show that the product feature extraction method proposed in this paper can effectively improve \( F1 \) and recall score of product feature extraction.
Keywords
Product feature extraction LDA Synonym recognition Shopping reviewsReferences
- 1.Popescu, A.M., Etzioni, O.: Extracting product features and opinions from reviews. In: Kao, A., Poteet, S.R. (eds.) Natural Language Processing and Text Mining, pp. 9–28. Springer, London (2007). https://doi.org/10.1007/978-1-84628-754-1_2CrossRefGoogle Scholar
- 2.Blei, D., Carin, L., Dunson, D.: Probabilistic topic models. IEEE Signal Process. Mag. 27(6), 55–65 (2010)Google Scholar
- 3.Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD-2004 - Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, United States, pp. 168–177. Association for Computing Machinery (2004)Google Scholar
- 4.Rana, T.A., Cheah, Y.-N.: Aspect extraction in sentiment analysis: comparative analysis and survey. Artif. Intell. Rev. 46(4), 459–483 (2016)CrossRefGoogle Scholar
- 5.Qian, L.: Research on approaches to opinion target extraction in opinion minging. Southeast University (2016)Google Scholar
- 6.Li, F., Han, C., Huang, M.: Structure-aware review mining and summarization. In: Proceedings of the 23rd International Conference on Computational Linguistics, vol. 2, pp. 653–661, Beijing, China. Tsinghua University Press (2010)Google Scholar
- 7.Qiu, G.A., Liu, B., Bu, J.J.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37(1), 9–27 (2011)CrossRefGoogle Scholar
- 8.Schouten, K., Frasincar, F.: Survey on aspect-level sentiment analysis. IEEE Trans. Knowl. Data Eng. J. 28(3), 813–830 (2016)CrossRefGoogle Scholar
- 9.Mei, Q., Ling, X., Wondra, M.: Topic sentiment mixture: modeling facets and opinions in weblogs. In: 16th International World Wide Web Conference, WWW 2007, Banff, AB, Canada, pp. 171–180. Association for Computing Machinery (2007)Google Scholar
- 10.Brody, S., Elhadad, N.: An unsupervised aspect-sentiment model for online reviews. In: NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference, Los Angeles, CA, United States, pp. 804–812. Association for Computational Linguistics (ACL) (2010)Google Scholar
- 11.Tian, J., Zhao, W.: Words similarity algorithm based on Tongyici Cilin in semantic web adaptive learning system. J. Jilin Univ. (Inf. Sci. Ed.) 28(06), 602–608 (2010)Google Scholar
- 12.Xu, L., Lin, H., Pan, Y.: Constructing the affective lexicon ontology. 2(2008), 602–608 (2010)Google Scholar
- 13.Lopez-Arevalo, I., Sosa-Sosa, V.J., Rojas-Lopez, F.: Improving selection of synsets from WordNet for domain-specific word sense disambiguation. Comput. Speech Lang. 41, 128–145 (2017)CrossRefGoogle Scholar
- 14.Xi, Y.: Recognizing the feature synonyms in product review. 30(4), 150–158 (2016)Google Scholar
- 15.Jeh, G., Widom, J.: SimRank: a measure of structural-context similarity. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Edmonton, Alta, Canada, pp. 538–543. Association for Computing Machinery (2002)Google Scholar
- 16.Mikolov, T., Chen, K., Corrado, G.: Efficient estimation of word representations in vector space. Comput. Sci. 1301–3781 (2013)Google Scholar
- 17.Luo, J., Wang, Q., Li, Y.: Word clustering based on word2vec and semantic similarity. In: Proceedings of the 33rd Chinese Control Conference, CCC 2014, Nanjing, China, pp. 804–812. IEEE Computer Society (2014)Google Scholar
- 18.Python Software Foundation. jieba0.39. https://pypi.org/project/jieba/. Accessed 28 Aug 2017
- 19.Natural Language Toolkit. NLTK3.4 documentation. http://www.nltk.org/. Accessed 7 Nov 2018
- 20.Turney, P.D., Littman, M.L.: Measuring praise and criticism: inference of semantic orientation from association. ACM Trans. Inf. Syst. 21(4), 315–346 (2003)CrossRefGoogle Scholar
- 21.Ma, B., Yan, Z.: Product features extraction of online reviews based on LDA model. 20(1), 98–103 (2014)Google Scholar
- 22.Wu, S.: Sentiment polarity unit extraction of web-based financial information based on dependency parsing. Jiangxi University of Finance & Economics (2015)Google Scholar
- 23.De Marneffe, M.C., Manning, C.D.: The Stanford typed dependencies representation. In: Coling 2008: Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation, pp. 1–8 (2008)Google Scholar