Classification of tweets data based on polarity using improved RBF kernel of SVM

被引：77

作者：

Gopi A.P. ^{[1
]}

Jyothi R.N.S. ^{[1
]}

Narayana V.L. ^{[1
]}

Sandeep K.S. ^{[1
]}

机构：

[1] Department of CSE, Vignan’s Nirula Institute of Technology and Science for Women, Palakaluru, Andhra Pradesh, Guntur

来源：

International Journal of Information Technology | 2023年 / 15卷 / 2期

关键词：

Feature extraction; Opinion mining; Score; Sentiment analysis; Text mining;

D O I：

10.1007/s41870-019-00409-4

中图分类号：

学科分类号：

摘要：

The sentiment analysis has gained its importance in recent years. People had improved their way of expressing their opinions about products, services, celebrities, and current topics in internet portals, blogs and social networks. The social network websites like Face book, Twitter, WhatsApp, LinkedIn and Hike messenger, providing the users to express their feelings by using the different symbols like smiley’s, funny faces, etc., These social media websites provide a platform to display peoples’ opinions on topics like movies, products, fashion trends, politics, technologies were expressed. The E-Commerce portals like Amazon, Flip Kart, Snap deal etc., help the people to express their opinions on products. A framework is proposed in this work to find the scores of the opinions and derive conclusions. The classification of opinions is called opinion mining, whereas deriving the scores for those opinions are called sentiment analysis. Here the Classification techniques are used for opinion mining and the scores to those opinions are given by taking a scale from –5 to +5.In this work, a movie review data set has been collected from the twitter reviews (http://ai.stanford.edu/~amaas/data/sentiment/) between the years 2003 and 2012. The Word net lexicon dictionary is used to compare the emotions for obtaining the score. In this paper, the proposed improved RBF kernel of SVM-performed with 98.8% of accuracy when compared with the existing SVM-RBF classifier and other models. © 2020, Bharati Vidyapeeth's Institute of Computer Applications and Management.

引用

页码：965 / 980

页数：15

共 50 条

[1]

Kim S.M., Hovy E., Determining the sentiment of opinions. In: Proceedings of the 20th international conference on Computational Linguistics, Association for Computational Linguistics, (2004)

[2]

Chaovalit P., Zhou L., Movie review mining: A comparison between supervised and unsupervised classification approaches, System Sciences, 2005. HICSS’05. Proceedings of the 38Th Annual Hawaii International Conference On. IEEE, (2005)

[3]

Radovanovic M., Ivanovic M., Text mining: approaches and applications, Novi Sad J Math, 38, (2008)

[4]

Gupta V., Lehal G.S., A survey of text mining techniques and applications, J Emerg Technol Web Intell, 1, (2009)

[5]

(, In: 3Rd IEEE International Conference on Digital Ecosystems and Technologies, 2009. DEST’09. IEEE, (2009)

[6]

Wang Z., Sun X., Document classification algorithm based on kernel logistic regression, In: 2010 2Nd International Conference on Industrial and Information Systems (IIS), 1, (2010)

[7]

Web data mining research: A survey. In: 2010 IEEE international conference on computational intelligence and computing research (ICCIC), IEEE, (2010)

[8]

Opinion mining and sentiment analysis, in Information Retrieval, 2, pp. 1-2, (2008)

[9]

Kumar L., Bhatia P.K., Text mining: concepts, process and applications, J Global Res Comput Sci, 4, (2013)

[10]

Zharmagambetov A.S., Pak A.A., Sentiment analysis of a document using deep learning approach and decision trees, 2015 Twelve International Conference on Electronics Computer and Computation (ICECCO). IEEE, (2015)

← 1 2 3 4 5 →