Recommender System Based On Collaborative Filtering Using Polarity Improvement in Sentiment Analysis

Subject Areas : Majlesi Journal of Telecommunication Devices

Alaleh Hosseini Charyani ¹ , Alireza Norouzi ²

1 - Iran
2 - Majlesi Branch, Islamic Azad University, Islamic Republic of Iran

Received: 2019-12-29 Accepted : 2020-01-05 Published : 2020-03-01

Keywords: grammatical features of texts, Sentiment Analysis, fuzzy method, text-mining techniques,

Abstract :

Sentiment Analysis, which is a new subfield of the processing of natural language and text mining, categorizes the texts based on the sentiment expressed in them. Sentiment plays a significant role in decision-making. So sentiment analysis technology has a broad scope for scientific applications. On the other hand, a huge amount of information in the world today is in the form of text. Therefore, text mining techniques are important. Exploring comments or analyzing sentiment as a branch of text mining, means finding the author's perspective on a specific subject. The Internet allows users to easily express their opinions and get informed about the opinions of others. The high volume and the lack of proper structure for the text of the comments provided on the web, make it difficult to use hidden knowledge within them. Therefore, it is important to provide methods that can prepare and provide this knowledge in a summarized and structured way. In this research, it has been tried to provide a fuzzy method for analyzing the following comments on news sites according to the text of the report. In this regard, it has been tried to investigate the relationship with the author's commentary and opinion in light of the subject of the text using the grammatical features of texts such as noun and verb, as well as sentimental load analysis of sentences. Subsequently, the method is evaluated by implementing it on the dataset collected from news and comments. The proposed method has 87% diagnosis accuracy.

References:

REFERENCES

[1] J.J. McCauley, J. Leskovec, "Hidden factors and hidden topics: understanding rating dimensions with review text", in: Seventh ACM Conference on Recommender Systems, RecSys ’13, Hong Kong, China, October 12–16, 2013, 2013, pp. 165–172.

[2] D.M. Blei, A.Y. Ng, M.I. Jordan, "Latent Dirichlet allocation", J. Mach.Learn. Res. 3 (2003) 993–1022,

[3] Y. Jo, A.H. Oh, "Aspect and sentiment unification model for online review analysis", in: Proceedings of the Forth International Conference on Web Search and Web Data Mining, WSDM 2011, Hong Kong,China, February 9–12, 2011, 2011, pp. 815–824.

[4] A. Popescu, O. Etzioni, "Extracting product features and opinions from reviews", in: Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, HLT/EMNLP 2005.

[5] B. Pang, L. Lee, S. Vaithyanathan," Sentiment classification using machine learning techniques", in: Proceedings of EMNLP,2002, pp. 79-86,

http://www.cs.cornell.edu/home/llee/papers/sentiment.pdf.

[6] I. Titov, R.T. McDonald, "A joint model of text and aspect ratings for sentiment summarization", in: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, ACL 2008, June 15–20, 2008, Columbus, Ohio, USA, 2008, pp. 308–316, http://www.aclweb.org/anthology/P08-1036.

[7] Y. Wu, M. Ester, Flame,"A probabilistic model combining aspect based opinion mining and collaborative filtering", in: Eighth ACM International Conference on Web Search and Data Mining, 2015,pp. 199–208.

[8] B. Pang, L. Lee, "Opinion mining and sentiment analysis", Found.Trends Inf. Retr. 2 (1–2) (2007) 1–135, http://dx.doi.org/10.1561/1500000011.

[9] W. W. H. Wang, "Opinion-enhanced collaborative filtering for recommender systems through sentiment analysis", New Review of Hypermedia and Multimedia", 2015.

[10] G. K. Mukund Deshpande, "Item-based top-N recommendation algorithms," ACM Transactions on Information Systems, vol. 22, pp. 143-177.