Machine learning based twitter data sentiment classification on real time ‘clean India mission’ tweets

  • Authors

    • sangeeta . M D University , Rohtak, Haryana, India
    • Nasib Singh Gill M D University , Rohtak, Haryana, India
    https://doi.org/10.14419/ijet.v7i4.19275

    Received date: September 9, 2018

    Accepted date: December 23, 2018

    Published date: November 14, 2018

  • SVM, Maxent, RF, Naïve Bayes, Clean India Mission, Swachh Bharat Abhiyan.

  • Abstract

    Social networking sites are popular medium to share opinion on various topics. Twitter is one of the social networking site used for tweet posting. Sentiment classification deal with finding the polarity of these tweets as positive, negative or neutral. This analysis can be useful in decision support in different ways. The aim of this paper is to discuss various machine learning algorithm for twitter sentiment classification, compare their results on the basis of Accuracy, Precision, Recall and F-Score. A real time data set for training and testing is created after extraction and cleaning of tweets on “Clean India Mission or Swachh Bharat Abhiyan”. “Clean India Mission” is a campaign by government of India to clean the country. This paper also compares machine learning algorithms with Bagging, Boosting and Random Forest ensemble approaches.

  • References

    1. BAC Le, and Huy Nguyen, “Twitter Sentiment Analysis Using Machine Learning Techniques”, Advanced Computational Methods for Knowledge Engineering, Advances in Intelligent Systems and Computing 358, DOI: 10.1007/978-3-319-17996-4_25, Springer In-ternational Publishing Switzerland 2015, pp. 279-289.
    2. Joseph Prusa, Tahhi M. Khoshgoftaar, David J. Dittman, “Using Ensemble Learners to Improve Classifier Performance on Tweet Sentiment Data”, Information Reuse and Integration (IRI), IEEE International Conference, 13-15 Aug. 2015, pp 252 – 257, INSPEC Accession Number: 15556647.
    3. Olga Kolchyna, Th´arsis T. P. Souza, Philip C. Treleaven and To-maso Aste, “Twitter Sentiment Analysis: Lexicon Method, Machine Learning Method and Their Combination”, Cornell University Li-brary, 18 Sep 2015, arXiv: 1507.00955.
    4. Abinash Tripathy, Ankit Agrawal, Santanu Kumar Rath, “Classification of sentiment reviews using n-gram machine learning approach”, in “Expert System With Applications”, ELSEVIER, 2016, pp. 117-126.
    5. M.S.Neethu, R. Rajasree, “Sentiment analysis in twitter using ma-chine learning techniques”, in “Computing, Communications and Networking Technologies (ICCCNT)”, 4th International Confer-ence, ISBN: 978-1-4799-3926-8,2013. https://doi.org/10.1109/ICCCNT.2013.6726818.
    6. K. Lakshmi Devi, P. Subathra, P. N. Kumar, “Tweet Sentiment Classification Using an Ensemble of Machine Learning Supervised Classifiers Employing Statistical Feature Selection Methods”, Pro-ceedings of the Fifth International Conference on “Fuzzy and Neu-ro Computing (FANCCO - 2015)”, Volume 415, pp 1-13, Nov 2015.( ISBN: 978-3-31927211-5 (Print) 978-3-319-27212-2.
    7. A. Agarwal, B. Xie, I. Vovsha, O. Rambow, R. Passonneau, “Sen-timent Analysis of Twitter Data”, LSM ’11 Proceedings of the workshop on Languages in Social Media, Columbia University New York, ISBN: 978-1-932432-96-1, pp. 30-38, 2011.
    8. Munir Ahmad, Shabib Aftab, Iftikhar Ali, “Sentiment Analysis of Tweets using SVM”, International Journal of Computer Applica-tions (0975 – 8887) Volume 177 –No.5, pp 25-29, Nov 2017.
    9. Bholane Savita Dattu, Prof.Deipali V. Gore, “A Survey on Senti-ment Analysis on Twitter Data Using Different Techniques”, (IJC-SIT) International Journal of Computer Science and Information Technologies, Vol. 6 (6) 2015, 5358-5362, ISSN 0975 9646, pp 5358 -5362.
    10. Nádia Félix Felipe da Silva, Luiz F.S. Coletta, Eduardo R. Hru-schka, Estevam R. Hruschka, “Using unsupervised information to improve semi supervised tweet sentiment classification”, Elsevier journal of Information Sciences, Volumes 355–356, 10 August 2016, Pages 348–365.
    11. Gaurangi Patil, Ms. Varsha Galande, Vedant Kekan, Kalpana Dan-ge, “Sentiment Analysis Using Support Vector Machine”, Interna-tional Journal of Innovative Research in Computer and Communica-tion Engineering, Vol. 2, Issue 1, January 2014, ISSN(Online): 2320-9801, pp. 42–49, 1999.
    12. A.Pak and P. Paroubek., “Twitter as a Corpus for Sentiment Analy-sis and Opinion Mining", In Proceedings of the Seventh Conference on International Language Resources and Evaluation, 2010, pp.1320-1326.
    13. T. Subbulakshmi, R. Regin Raja, “An Ensemble Approach For Sen-timent Classification: Voting For Classes and Against Them”, IC-TACT Journal On Soft Computing, July 2016, Volume 06, Issue: 04, ISSN: 2229-6956 (ONLINE), pp 1281-1286.
    14. Narr, Sascha, Michael Hulfenhaus, and Sahin Albayrak. "Language-independent twitter sentiment analysis." Knowledge Discovery and Machine Learning (KDML), LWA (2012): 12-14.
    15. Mohammad Rezwanul Huq, Ahmad Ali, Anika Rahman , “Senti-ment Analysis on Twitter Data using KNN and SVM”, In (IJACSA) International Journal of Advanced Computer Science and applications, Vol. 8, No. 6, pages 19-25, 2017.
    16. A. Kumar and T. Mary Sebastian, “Sentiment Analysis on Twitter”, IJCSI International Journal of Computer Science Issues, Vol. 9, Is-sue 4, No 3,.July 2012, ISSN (Online): 1694-0814.
    17. G. Patil, V. Galande, V. Kekan, K. Dange, “Sentiment Analysis Using Support Vector Machine”, International Journal of Innova-tive Research in Computer and Communication Engineering , Vol. 2, Issue 1, January 2014, pp 2607-2612.
    18. Nikhil R, Nikhil Tikoo, Sukrit Kurle, Hari Sravan Pisupati, Prasad G R, “A Survey on Text Mining and Sentiment Analysis for Un-structured Web Data”, International Journal of Emerging Technolo-gies and Innovative Research(JETIR), April 2015, Volume 2, Issue 4 , ISSN-2349-5162, pp. 1292-1296.
    19. Gaurangi Patil, Ms. Varsha Galande, Vedant Kekan, Kalpana Dan-ge, “Sentiment Analysis Using Support Vector Machine”, Interna-tional Journal of Innovative Research in Computer and Communica-tion Engineering, Vol. 2, Issue 1, January 2014, ISSN(Online): 2320-9801, pp. 42–49, 1999.
    20. Arockia Xavier Annie R, Vignesh Mohan, Sree Harissh Venu, “Sen-timent Analysis Applied to Airline Feedback to Boost Customer's Endearment”, second International Conference on Multidisciplinary Innovation For Sustainability And Growth (MISG 2015), ISBN: 978-969-9948-31-2, Vol. 2, pp 219-232, 2015.
    21. Christos Troussas, Maria Virvou, Kurt Junshean Espinosa, Kevin Llaguno, Jaime Caro, “Sentiment analysis of Facebook statuses us-ing Naive Bayes classifier for language” , published in “ Information, Intelligence, Systems and Applications (IISA)” , Fourth International Conference , 2013, ISBN: 978-1-4799-0771-7. https://doi.org/10.1109/IISA.2013.6623713.
    22. Akshi Kumar, Teeja Mary Sebastian, “Sentiment Analysis on Twit-ter”, IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 4, No 3, July 2012, ISSN: 1694-0814, pp. 372-378.
    23. Walaa Medhat, Ahmed Hassan, Hoda Korashy, “Sentiment analysis algorithms and applications: A survey”, Ain Shams Engineering Journal, April 2014, Vol 5, issue 4, pp. 1093-1113. https://doi.org/10.1016/j.asej.2014.04.011.
    24. Xiang Ji, Soon Ae Chun, James Geller, “Monitoring Public Health Concerns Using Twitter Sentiment Classifications”, in IEEE Inter-national Conference on Healthcare Informatics, 2013, 978-0-7695-5089-3/13, pp. 235-244.
    25. Lina L. Dhande, Dr. Prof. Girish K. Patnaik, “Analyzing Sentiment of Movie Review Data using Naive Bayes Neural Classifier”, in In-ternational Journal of Emerging Trends & Technology in Computer Science (IJETTCS), Volume 3, Issue 4 July-August 2014, ISSN 2278-6856, pp. 313-320.
    26. Yun Wan, Dr. Qigang GAO, “An Ensemble Sentiment Classifica-tion System of Twitter Data for Airline Services Analysis”, IEEE 15th International Conference on Data Mining Workshops, 978-1-4673-84933/15, 2015, pp 1318-1325.

  • Downloads

  • How to Cite

    ., sangeeta, & Singh Gill, N. (2018). Machine learning based twitter data sentiment classification on real time ‘clean India mission’ tweets. International Journal of Engineering and Technology, 7(4), 4737-4742. https://doi.org/10.14419/ijet.v7i4.19275