Open Access   Article

Aspect-Opinion Identification and Classification Using Custom Heuristic Rules

T. U. Kadam1 , P. Kaur2

1 Dept. of CSE, Jawaharlal Nehru Engineering College, Aurangabad, India.
2 Dept. of IT, Jawaharlal Nehru Engineering College, Aurangabad, India .

Section:Research Paper, Product Type: Journal Paper
Volume-6 , Issue-4 , Page no. 76-80, Apr-2018

CrossRef-DOI:   https://doi.org/10.26438/ijcse/v6i4.7680

Online published on Apr 30, 2018

Copyright © T. U. Kadam, P. Kaur . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

View this paper at   Google Scholar | DPI Digital Library

Citation

IEEE Style Citation: T. U. Kadam, P. Kaur, “Aspect-Opinion Identification and Classification Using Custom Heuristic Rules”, International Journal of Computer Sciences and Engineering, Vol.6, Issue.4, pp.76-80, 2018.

MLA Style Citation: T. U. Kadam, P. Kaur "Aspect-Opinion Identification and Classification Using Custom Heuristic Rules." International Journal of Computer Sciences and Engineering 6.4 (2018): 76-80.

APA Style Citation: T. U. Kadam, P. Kaur, (2018). Aspect-Opinion Identification and Classification Using Custom Heuristic Rules. International Journal of Computer Sciences and Engineering, 6(4), 76-80.

VIEWS PDF XML
103 121 downloads 21 downloads
  
  
           

Abstract

Users opinion about different entities forms the huge repository of data over internet. It is highly impossible to accurately monitor and find what actually a user wants to say about an entity from this large amount of data. Data analyst these days concentrates on finely analyzing opinions about particular entity and for this reason the extraction of aspects and its corresponding opinions of that entity are important. This work concentrates on identifying aspects and their corresponding opinion from the provided user opinions which helps to obtain fine grained knowledge about the entity. To obtain aspects and related opinions custom heuristic rules are created by using regular expression on the parts-of-speech tagging. The created rules are provided to Stanford natural language processing (SNLP) classifier and finds association of aspect words and opinion words from the opinion corpus. The classification is done by SNLP classifier and Naïve Bayes (NB) classifier. Identification of aspects and aspect specific opinions are accurately obtained using custom heuristic rules applied over SNLP compared to NB.

Key-Words / Index Term

Aspects, Opinions, Heuristic Rules, SNLP, NB.

References

[1] Quan Fang, Changsheng Xu, Jitao Sang, M. Shamim Hossain and Ghulam Muhammad,”Word-of-mouth understanding: entity-centric multimodal aspect-opinion mining in social media,” IEEE transaction on multimedia, volume 17.No. 12, pp. 2281-2296, December 2015.
[2] Masud Karim, Rashedur M. Rahman, “Decision tree and naïve bayes algorithm for classification and generation of actionable knowledge for direct marketing,” Journal of Software Engineering and Applications, 6, pp 196-206, 2013.
[3] F. Chua, W. Cohen, J. Betteridge, E. Lim, “Community-Based Classification of Noun Phrases in Twitter,” In the Proceedings of the 21st international ACM conference of information and knowledge management (CIKM’ 12), pp 1702-1706, 2012.
[4] Richard Socher and et. Al, “Recursive deep models for semantic compositionality over sentiment a Treebank,” In the Proceedings of the conference on empirical methods in natural language processing, EMNLP’13, 2013.
[5] Bo Pang, Lillian Lee, Shivakumar Vaithyanathan, “Thumbs up? Sentiment Classification using Machine Learning Techniques,” In Proceedings of the EMNLP 2002, pp. 79–86, 2002.
[6] Sida Wang and Christopher Manning, “Baselines and bigrams: simple, good sentiment and topic classification,” In Proceedings of the 50th Annual Meeting of the Association for computational Linguistics (ACL’12), volume 2, July 08 – 14, pp 90-94, 2012.
[7] B. Liu and L. Zhang,“A survey of opinion mining and sentiment analysis,” in Mining Text Data. New York, NY, USA: Springer, 2012, pp. 415–463, 2012.
[8] Moghaddam, S., Popowich F., “Opinion polarity identification through adjectives”, CoRR arXiv: 1011.4623 (2010).
[9] S. Moghaddam and M. Ester, “On the design of lda models for aspectbased opinion mining,” In the Proceedings of 21st ACM International Conference on Information and Knowledge Management (CIKM’12), pp. 803–812, 2012.
[10] W. X. Zhao, J. Jiang, H. Yan, and X. Li, “Jointly modeling aspects and opinions with a MaxEnt-LDA hybrid,” in the proceedings of the conference on the Empirical Methods in Natural Language Processing (EMNLP 2010), MIT, Massachusetts, USA, pp. 56–65, 2010.
[11] A. Mukherjee and B. Liu, “Aspect extraction through semi-supervised modeling,” In the Proceedings of Assoc. Comput. Linguistics, 2012, pp. 339–348, 2012.
[12] M. Hu and B. Liu, “Mining and summarizing customer reviews,” In the Proceedings of the Tenth ACM SIGMOD International Conference on Knowledge Discovery and Data Mining (KDD 2004), pp. 168–177, 2004.
[13] Qian Liu, Zhiqiang Gao, Bing Liu3 and Yuanlin Zhang, “Automated Rule Selection for Aspect Extraction in Opinion Mining,” In the Proceedings of Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), pp 1291-1297, 2015.
[14] Y. Yang, C. Chen, M. Qiu, F. s. Bao, “Aspect extraction from product reviews using category hierarchy information,” In the Proceedings of the 15th Conference of the European Chapter of Association for Computational Linguistics: Volume 2, Short Papers, pages 675–680, 2017.
[15] Y. Fang, L. Si, N. Somasundaram, and Z. Yu, “Mining contrastive opinions on political texts using cross-perspective topic model,” In the Proceedings of the Fifth ACM WSDM 2012, pp. 63–72, 2012.
[16] A. McCallum and K. Nigam, “A comparison of event models for naïve bayes text classification,” In the Proceedings of the ICML/AAAI-98 workshop on learning for text categorization, Madison, WI, pp. 41–48, 26–27 July 1998.