Fuzzy Algorithm Based Sentiment Analysis: Enhancing Accuracy and Interpretability
Keywords:
Sentiment Analysis, Machine Learning, Fuzzy Logic, Opinion Mining, TF-IDFAbstract
Sentiment analysis is the technique of determining the point of view, polarity, and intensity of a text. A poll found that 93% of consumers read online evaluations before making a decision. Manually analysing these judgements is challenging. To determine the review's overall sentiment or thinking polarity, sentiment analysis may be employed. This study's goal is to classify product assessment qualities as positive, negative, or neutral. Polarity labelling, feature extraction, and associated descriptor extraction are all included. The suggested method expands on feature-based categorisation by considering the impact of different linguistic hedges. In order to mimic the effects of modifiers, concentrators, and dilators, this technique uses fuzzy functions. The system was put to the test, and the outcomes show how well fuzzy logic based sentiment analysis performs.
References
El-Nasr MS, Yen J, Ioerger TR. Flame: fuzzy logic adaptive model of emotions. Auton Agents Multi-agent Syst. 2000 Sep; 3(3): 219–57.
Hearst MA. Direction-based text interpretation as an information access refinement. Text-based intelligent systems: current research and practice in information extraction and retrieval. 1992 Jul 1; 257–74.
Pang B, Lee L. Opinion mining and sentiment analysis. Found Trends Inf Ret. 2008 Jul 6; 2(1–2): 1–35.
Turney PD. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032. 2002 Dec 11.
Dzogang F, Lesot MJ, Rifqi M, Bouchon-Meunier B. Expressions of graduality for sentiments analysis: A survey. In IEEE International Conference on Fuzzy Systems. 2010 Jul 18; 1–7.
Cakmak O, Kazemzadeh A, Yildirim S, Narayanan S. Using interval type-2 fuzzy logic to analyze Turkish emotion words. In Proceedings of the IEEE 2012 Asia pacific signal and information processing association annual summit and conference. 2012 Dec 3; 1–4.
Varghese R, Jayasree M. A survey on sentiment analysis and opinion mining. International Journal of Research in Engineering and Technology (IJRET). 2013 Nov; 2(11): 312–7.
Pang B, Lee L. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. arXiv preprint cs/0409058. 2004 Sep 29.
Pak A, Paroubek P. Twitter as a corpus for sentiment analysis and opinion mining. In LREC. 2010 May 17; 10(2010): 1320–1326.
Wilson T, Wiebe J, Hoffmann P. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of human language technology conference and conference on empirical methods in natural language processing. 2005 Oct; 347–354.
Kulkarni S, Nikumbh PJ, Nikam S. S-ANFIS: Sentiment aware adaptive network-based fuzzy inference system for Predicting Sales Performance using Blogs/Reviews.
Tetsuya Nasukawa, Jeonghee Yi. Sentiment Analysis: Capturing Favorability Using Natural Language Processing. Proceedings of the 2nd international conference on Knowledge capture. 2003 Oct; 70–77.
Yang CC, Wong YC, Wei CP. Classifying web review opinions for consumer product analysis. In Proceedings of the 11th International Conference on Electronic Commerce. 2009 Aug 12; 57–63.
Bollegala D, Weir D, Carroll J. Cross-domain sentiment classification using a sentiment sensitive thesaurus. IEEE Trans Knowl Data Eng. 2012 May 22; 25(8): 1719–31.
Mukherjee S, Bhattacharyya P. Feature specific sentiment analysis for product reviews. In International conference on intelligent text processing and computational linguistics. 2012 Mar 11; 475–487. Berlin, Heidelberg: Springer Berlin Heidelberg.
Zadeh LA. Calculus of fuzzy restrictions, fuzzy sets and their applications to cognitive and decision processes. New York: Academic; 1975.
Grieve J, Biber D, Friginal E, Nekrasova T. Variation among blogs: A multi-dimensional analysis. In: Genres on the web: Computational models and empirical studies. 2011; 303–22. Dordrecht: Springer.
