We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 November 2024
Reseach Article

An Analysis of Sentimental Data using Machine Learning Techniques

by Surbhi Chandhok, Romil Anand, Soumay Gupta, Aatif Jamshed
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 166 - Number 3
Year of Publication: 2017
Authors: Surbhi Chandhok, Romil Anand, Soumay Gupta, Aatif Jamshed
10.5120/ijca2017913955

Surbhi Chandhok, Romil Anand, Soumay Gupta, Aatif Jamshed . An Analysis of Sentimental Data using Machine Learning Techniques. International Journal of Computer Applications. 166, 3 ( May 2017), 35-39. DOI=10.5120/ijca2017913955

@article{ 10.5120/ijca2017913955,
author = { Surbhi Chandhok, Romil Anand, Soumay Gupta, Aatif Jamshed },
title = { An Analysis of Sentimental Data using Machine Learning Techniques },
journal = { International Journal of Computer Applications },
issue_date = { May 2017 },
volume = { 166 },
number = { 3 },
month = { May },
year = { 2017 },
issn = { 0975-8887 },
pages = { 35-39 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume166/number3/27652-2017913955/ },
doi = { 10.5120/ijca2017913955 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:12:44.616608+05:30
%A Surbhi Chandhok
%A Romil Anand
%A Soumay Gupta
%A Aatif Jamshed
%T An Analysis of Sentimental Data using Machine Learning Techniques
%J International Journal of Computer Applications
%@ 0975-8887
%V 166
%N 3
%P 35-39
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Sentiment analysis, basically, comprises of identifying different opinions or emotions in source text and then classifying them in its accordance. Social media generates extensive sentiment rich dataset in the form of Social media in through status updates, tweets, short video clips, blog posts etc. At the same time, it is relatively more difficult to do a Twitter estimation investigation when contrasted with general assessment examination. This is because of the presence of foul words, slang language and incorrect spellings. The maximum character limit per tweet in Twitter is 140. There are two strategies used to analyse sentiments, emotions and/or opinions from the source file. These two strategies are: Approach based on knowledge Approach based on learning of machine. Throughout this paper, we’ve tried to analyse the posts of twitter related to a wide range of electronic products such as mobiles, laptops, video games television sets etc. using Machine Learning approach. During the time spent doing notion investigation in a specific area, it is conceivable to distinguish and make sense of the impact of space data as per the estimation order. We've additionally presented another element vector, in order to just group the tweets as plain constructive, pessimistic and infer people groups' feeling about items.

References
  1. Y. Mejova, “Sentiment analysis: An overview,” Comprehensive exam paper, available on http://www.cs.uiowa.edu/˜ymejova/publications/CompsYelenaMejova. pdf [201002- 03], 2009.
  2. P. D. Turney, “Thumbs up or thumbs down?: semantic orientation applied to unsupervised relegation of reviews,” in Proceedings of the 40th annual meeting on sodality for computational linguistics, pp. 417–424, Sodality for Computational Linguistics, 2002.
  3. E. Boiy, P. Hens, K. Deschacht, and M.-F. Moens, “Automatic sentiment analysis in on-line text,” in Proceedings of the 11th International Conference on Electronic Publishing, pp. 349–360, 2007.
  4. J. Kamps, M. Marx, R. J. Mokken, and M. De Rijke, “Using wordnet to quantify semantic orientations of adjectives,” 2004.
  5. C. Fellbaum, “Wordnet: An electronic lexical database (language, verbalization, and communication),” 1998.
  6. D. Pucci, M. Baroni, F. Cutugno, and A. Lenci, “Unsupervised lexical supersession with a word space model,” in Proceedings of EVALITA workshop, 11th Congress of Italian Sodality for Artificial Astuteness, Citeseer, 2009.
  7. A. Balahur, J. M. Hermida, and A. Montoyo, “Building and exploiting emotinet, an erudition base for emotion detection predicated on the appraisal theory model,” Affective Computing, IEEE Transactions on, vol. 3, no. 1, pp. 88–101, 2012.
  8. C. Strapparava and R. Mihalcea, “Semeval-2007 task 14: Affective text,” in Proceedings of the 4th International Workshop on Semantic Evaluations, pp. 70–74, Sodality for Computational Linguistics, 2007.
  9. G. Vinodhini and R. Chandrasekaran, “Sentiment analysis and opinion mining: A survey,” International Journal, vol. 2, no. 6, 2012.
  10. L. Barbosa and J. Feng, “Robust sentiment detection on twitter from partial and strepitous data,” in Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pp. 36–44, Sodality for Computational Linguistics, 2010.
  11. Z. Niu, Z. Yin, and X. Kong, “Sentiment relegation for microblog by machine learning,” in Computational and Information Sciences ( ICCIS), 2012 Fourth International Conference on, pp. 286–289, IEEE, 2012.
  12. P. Domingos and M. Pazzani, “On the optimality of the simple bayesian classifier under zero-one loss,” Machine Learning, vol. 29, no. 2-3 , pp. 103–130, 1997.
  13. A. Celikyilmaz, D. Hakkani-Tur, and J. Feng, “Probabilistic model-predicated sentiment analysis of twitter messages,” in Verbalized Language Technology Workshop (SLT), 2010 IEEE, pp. 79–84, IEEE, 2010.
  14. Y. Wu and F. Ren, “Learning sentimental influence in twitter,” in Future Computer Sciences and Application (ICFCSA), 2011 International Conference on, pp. 119– 122, IEEE, 2011.
Index Terms

Computer Science
Information Sciences

Keywords

Twitter Sentiment Analysis Machine Learning Techniques