Sentiment Classification Of Movie Review And Twitter Data Using Machine Learning

Prafulla Mohapatra; Rohit Kumar Singh; Shashank Pandey; PrashanthAnand Kumar; Mrs.Asha K N; A.Ravi Kumar

doi:https://doi.org/10.14445/22492593/IJCOT-V9I3P301

Research Article | Open Access | Download PDF

Volume 9 | Issue 3 | Year 2019 | Article Id. IJCOT-V9I3P301 | DOI : https://doi.org/10.14445/22492593/IJCOT-V9I3P301

Sentiment Classification Of Movie Review And Twitter Data Using Machine Learning

Prafulla Mohapatra, Rohit Kumar Singh, Shashank Pandey, PrashanthAnand Kumar, Mrs.Asha K N, A.Ravi Kumar

Citation :

Prafulla Mohapatra, Rohit Kumar Singh, Shashank Pandey, PrashanthAnand Kumar, Mrs.Asha K N, A.Ravi Kumar, "Sentiment Classification Of Movie Review And Twitter Data Using Machine Learning," International Journal of Computer & Organization Trends (IJCOT), vol. 9, no. 3, pp. 1-8, 2019. Crossref, https://doi.org/10.14445/22492593/IJCOT-V9I3P301

Abstract

Over three billion people use some form of social media in their day to day lives. Therefore, it is not unwise to say that social media is one of the single largest collection of data about humans present, in the world currently. Sentiment analysis is one of the most common operations done on social media data. In this paper, we perform sentiment analysis, using a variety of vectorizers and classifiers to see which combination yields the highest accuracy. Analysis is performed on Twitter and movie review data. The two data sets are inherently different and therefore there could be a difference between the accuracies. The front end of this application is web based. Twitter and movie review data are collected from two API’s in real time and then the different tweets/reviews are classified as either being positive or negative. This is then presented in the form of a donut graph.

Keywords

Sentiment Analysis, Machine Learning, Information Retrieval, Opinion Mining and Natural language processing.

References

[1] Go, A., Bhayani, R., & Huang, L. (2009). Twitter sentiment classification using distant supervision. CS224N project report, Stanford, 1(12), 2009.

[2] Willett, P. (2006). The Porter stemming algorithm: then and now. Program, 40(3), 219-223.

[3] Karimov, R., Samkova, M., Nikitina, S., & Akinin, A. (2016). Using a hybrid algorithm for lemmatization of a diachronic corpus. In CEUR workshop proceedings (Vol. 1886, pp. 1-8).

[4] Church, K. W. AT&T Bell Laboratories Murray Hill, NJ USA kwc@ research. att. com.

[5] Saif, H., Fernandez, M., He, Y., & Alani, H. (2014). On stopwords, filtering and data sparsity for sentiment analysis of twitter.