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

[21]

Sudhakaran P., Et al., Research directions, challenges and issues in opinion mining, Int J Adv Sci Technol, 60, (2013)

[22]

Jagtap V.S., Pawar K., Analysis of different approaches to sentence-level sentiment classification, Int J Sci Eng Technol, 2, (2013)

[23]

Gupte A., Et al., Comparative study of classification algorithms used in sentiment analysis, Int J Comput Sci Inf Technol, 5, (2014)

[24]

Hasan K.M., Azharul R.M., Sentiment detection from Bangla text using contextual valency analysis, 17Th International Conference on Computer and Information Technology (ICCIT), (2014)

[25]

Asghar M.Z., Khan A., Sentiment classification through semantic orientation using SentiWordNet, Life Sci J, 11, (2014)

[26]

Medhat W., Hassan A., Korashy H., Sentiment analysis algorithms and applications: a survey, (2014)

[27]

Patil G., Et al., Sentiment analysis using support vector machine, Int J Innov Res Comput Commun Eng, 2, (2014)

[28]

Singh S.K., Et al., Sentiment analysis of twitter data set: survey, Int J Appl Eng Res, 9, (2014)

[29]

Sharma R., Nigam S., Jain R., Polarity detection at sentence level, Int J Comput Appl, 86, (2014)

[30]

Lin L., Opinion mining and sentiment analysis in social networks: A retweeting structure-aware approach, In: Proceedings of the IEEE/ACM 7Th International Conference on Utility and Cloud Computing. IEEE Computer Society, (2014)

← 1 2 3 4 5 →