Journal of Digital Information Management


Vol No. 18 ,Issue No. 3 2020

A Graph-Based Approach for Aspect Extraction from Online Customer Reviews
Rakesh Kumar, Aditi Sharan
Jawaharlal Nehru University, New Delhi & India
Abstract: E-commerce websites have become main market players in the 21st century due to advancement in the internet technology. Apart from buying products online, customers are also providing reviews on the products purchased by them. These reviews help new customers to buy various products according to their needs, liking, and preferences. However, millions of reviews are added by the customer on a daily basis. To extract meaningful information manually from these huge amounts of reviews is a tough task. So, it is required to develop an automatic analytics tool for the review sentences. Aspect extraction is one of the vital tasks in the process of meaningful information extraction from the products having various entities. In this work, a novel product aspect extraction approach has been proposed which utilize a graphbased technique with the integration of statistical and semantic information. The analysis of experimental results shows that the proposed approach is efficient and effective in comparison to the state of art methods.
Keywords: Opinion Mining, Feature Extraction, PageRank Algorithm, Online Product Reviews A Graph-Based Approach for Aspect Extraction from Online Customer Reviews
DOI:https://doi.org/10.6025/jdim/2020/18/3/99-108
Full_Text   PDF 932 KB   Download:   296  times
References:

[1] Balahur, A., Hermida, J. M., Montoyo, A. (2012). Detecting implicit expressions of emotion in text: a comparative analysis, Decision Support Systems, 53, 742– 753.
[2] Ghose, A., Ipeirotis, P. G., Li, B. B. (2014). Examining the impact of ranking on consumer behavior and search engine revenue, Manag. Sci. 60 (7) 1632–1654.
[3] Liu, B., Hu, M., Cheng, J. (2005). Opinion observer: analyzing and comparing opinions on the web, In: Proceedings of International Conference of World Wide Web, Publishing, 2005, p. 342–351.
[4] Lin, C., He, Y., Everson, R., Ruger, S. (2012). Weakly supervised joint sentiment-topic detection from text, IEEE Transactions on Knowledge and Data Engineering 24 (6) 1134–1145.
[5] Wei, C. P., Chen, Y. M., Yang, C. S., Yang, C. C. (2010). Understanding what concerns consumers: a semantic approach to product feature extraction from consumer reviews, Information Systems and E-Business Management, 8 (2) 149–167.
[6] Eirinaki, M., Pisal, S., Singh, J. (2012). Feature-based opinion mining and ranking. J. Comput. Syst. Sci., 78, 1175–1184.
[7] Qiu, G., Liu, B., Bu, J., Chen, C. (2011). Opinion word expansion and target extraction through double propagation, Comput. Linguist. 37 (1) 9–27.
[8] Somprasertsri, G., Lalitrojwong, P. (2010). Mining feature- opinion in online customer eviews for opinion summarization, J. Univers. Comput. Sci. 16 (6) 938–955.
[9] Wang, G. A., Jiao, J., Abrahams, A. S., Fan, W., Zhang, Z. (2013). Expertrank:, A topic-aware expert finding algorithm for online knowledge communities, Decis. Support
Syst. 54 (3) 1442–1451.
[10] Golub, G. H., Van Loan, C. F. (2012). Matrix Computations, Johns Hopkins University Press, Baltimore, MD, 2012.
[11] Titov, I., McDonald, R. (2008). A joint model of text and aspect ratings for sentiment summarization, in: Proceedings of the Annual Meeting on Association for Computational
Linguistics and the Human Language Technology Conference (ACL-HLT), Publishing, p. 308–316.
[12] IRESEARCH, China internet shopping market report in 2013, 2014-5, <http://ec.iresearch.cn/shopping/20140114/224908.shtml>
[13] Toutanova, K., Klein, D., Manning, C. D., Singer, Y. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network, in: Proceedings of HLT-NAACL, Publishing, p. 252–259.
[14] Kang, Y., Zhou, L. (2017). RubE: Rule-based methods for extracting product features from online consumer reviews. Inf. Manag. 54, 166–176.
[15] Li, S., Zhou, L., Li, Y. (2015). Improving aspect extraction by augmenting a frequency-based method with web-based similarity measures. Inf. Process. Manag. 51, 58–67.
[16] Long, C., Zhang, J., Zhut, X. (2010). A Review Selection Approach for Accurate Feature Rating Estimation. In: Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Beijing, China, 23–27 August 2010; Association for Computational Linguistics: Stroudsburg, PA, USA, p. 766–774.
[17] Aljukhadar, M., Senecal, S., Daoust, C. E. (2012). Using recommendation agents to cope with information overload, Int. J. Electron. Commer. 17 (2) 41–70.
[18] Hu, M., Liu, B. (2004). Mining and summarizing customer reviews, in: Proceedings of International Conference on Knowledge Discovery and Data Mining, Publishing, ACM SIGKDD, p. 168–177.
[19] Hu, M., Liu, B. (2004). Mining opinion features in customer reviews, In: Proceedings of 19th National Conference on Artificial Intelligence, Publishing, AAAI Press, p. 755–760.
[20] Popescu, A. M., Etzioni, O. (2005). OPINE: Extracting Product Features and Opinions from Reviews. In: Proceedings of the HLT/EMNLP on Interactive Demonstrations, Vancouver, BC, Canada, 7 October 2005; Association for Computational Linguistics: Stroudsburg, PA, USA, p. 32–33.
[21] Poria, S., Ofek, N., Gelbukh, A., Hussain, A., Rokach, L. (2014). Dependency tree-Based rules for concept-level aspect-based sentiment analysis. In Semantic Web Evaluation Challenge; Springer: Cham, Switzerland, p. 41–47. 
[22] Su, Q., Xiang, K., Wang, H., Sun, B., Yu, S. (2006). Using pointwise mutual information to identify implicit features in customer reviews, In: Proceedings of 17th International Conference on Computer Processing of Oriental Languages, Publishing, p. 22–30.
[23] Qiu, G., Liu, B., Bu, J., Chen, C. (2009). Expanding domain sentiment lexicon through double propagation. In: Proceedings of the 21st International Jont Conference on Artifical Intelligence, Pasadena, CA, USA, 11–17 July 2009; Morgan Kaufmann Publishers Inc.: San Francisco, CA, USA, p. 1199–1204.
[24] Lau, R.Y., Li, C., Liao, S. S. (2014). Social analytics: learning fuzzy product ontologies for aspect-oriented sentiment analysis, Decis. Support Syst. 65, p. 80–94.
[25] Rana, T. A., Cheah, Y. N. (2017). A Two-Fold Rule- Based Model for Aspect Extraction. Expert Syst. Appl. 89, 273–285.
[26] Brin, S., Page, L. (1998). The anatomy of a largescale hypertextual web search engine, Comput. Netw. ISDN Syst. 30 (1) 107–117.
[27] Brody, S., Elhadad, N. (2010). An unsupervised aspect- sentiment model for online reviews, In: Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics, Publishing, Association for Computational Linguistics, p. 804– 812.
[28] Scaffidi, C., Bierhoff, K., Chang, E., Felker, M., Ng, H., Jin, C. (2007). Red Opal: Product-feature scoring from reviews. In: Proceedings of the 8th ACM Conference on Electronic Commerce, San Diego, CA, USA, 11–15 June 2007; ACM: New York, NY, USA, p. 182–191.
[29] Su, S. H., Lynn, K. T. (2013). Extracting Product Features and Opinion Words Using Pattern Knowledge in Customer Reviews. Sci. World J. 2013, 394758:1– 394758:5.
[30] Thet, T. T., Na, J. C., Khoo, C. S. (2010). Aspectbased sentiment analysis of movie reviews on discussion boards, Journal of Information Science, 36 (6) 823–848.
[31] Fan, W. G., Gordon, M. D. (2014). The power of social media analytics, Commun. ACM 57 (6), p. 74–81.
[32] Fu, X., Liu, G., Guo, Y., Wang, Z. (2013). Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon, Knowledge Based Systems, 37, 186–195.
[33] Wu, Y., Zhang, Q., Huang, X., Wu, L. (2009). Phrase dependency parsing for opinion mining, In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, (Singapore), p. 1533–1541.
[34] Chen, Y. -C., Shang, R. -A., Kao, C. -Y. (2009). The effects of information overload on consumers subjective state towards buying decision in the internet shopping environment, Electron. Commer. Res. Appl. 8 (1) 48–58.
[35] Yan, Z., Xing, M., Zhang, D., Ma, B. (2015). EXPRS: An extended pagerank method for product feature extraction from online consumer reviews. Inf. Manag. 52, 850– 858.
[36] Zhai, Z., Liu, B., Xu, H., Jia, P. (2011). Constrained LDA for grouping product features in opinion mining, In: Proceedings of 15th Pacific–Asia Conference, Advances in Knowledge Discovery and Data Mining, p. 448–459.
[37] Zhang, L., Liu, B., Lim, S. H., O Brien-Strain, E. (2010). Extracting and ranking product features in opinion documents. In: Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Beijing, China, 23–27 August 2010; Association for Computational Linguistics: Stroudsburg, PA, USA, p. 1462–1470.
[38] Zhuang, L., Jing, F., Zhu, X. Y. (2006). Movie review mining and summarization. In: Proceedings of the 15th ACM International Conference on Information and Knowledge
Management, Arlington, VA, USA, 06–11 November 2006; ACM: New York, NY, USA, p. 43–50.
[39] Poria, Soujanya., Cambria, Erik., Ku, Lun-Wei., Gui, Chen., Gelbukh, Alexander. (2014). A Rule-Based Approach to Aspect Extraction from Product Reviews. In: Proceedings of the Second Workshop on Natural Language Processing for Social Media, Dublin, Ireland, August p. 28-37.
[40] Rana, T. A., Cheah, Y. N. (2015). Hybrid rule-based approach for aspect extraction and categorization from customer reviews. In: Proceedings of 9th International Conference on IT in Asia (CITA), Kota Samarahan, Malaysia, (August) p. 1-5.
[41] Ansari, Gunjan., Saxena, Chandni., Ahmad, Tanvir., Doja, M. N. (2020). Aspect Term Extraction using Graphbased Semi-Supervised Learning, In: Proceedings of International Conference on Computational Intelligence and Data Science (ICCIDS 2019), (February) p. 2080-2090.