Sentiment Analysis using Machine Learning through Twitter Streaming API

  • Authors

    • P Akilandeswari
    • R Harshita
    • Sumanth. KO.M
    2018-07-20
    https://doi.org/10.14419/ijet.v7i3.12.17781
  • Continuous learning, Opinion mining, Sentiment analysis, Social media analysis, Streaming data.

  • Social media allows to share the experiences with many best suggestions and provides opportunities to share the ideas about any topics at any time. In the current trending, twitter is used to gather different kinds of information as user need and it is a social network service which enables the user for better communication and gaining of knowledge. Accurate representation of the user interactions can be done based on the facts sematic content. The pre-processed tweets which are stored in database are been identified and classified whether it relates to the user keywords related posts. The best suggestion using polarity can be predicted using the user keywords. For the interactive automatic system which predicts the tweets posted by the user this system deals with the challenges that appears during the sentimental analysis. It deals with effective study prior to the subjective information. The basic task in this is to identify the polarity of a given tweet in the sentence whether it is positive, negative or neutral. However the polarity of the tweets has been identified, it was difficult for us to check with the meaningless data. To address this challenge the extracted tweets are been pre-processed by replacing the full form instead of short term words. The better performance can be achieved using more training data. However the analysis was frequently done using the previously stored data, it was a challenging task to do it using the streaming data. There are very few works related to the sentiment analysis using online streaming data. In this paper, we propose that the sentiment analysis can be improved using the online streaming data. For online streaming data all the data related to the given topic will be collected according to the current data in the twitter. For better up-to-date analysis, the streaming data is used and can achieve better results. In contrast by conducting the continuous learning from the streaming data, this approach provides better results than the traditional way of using the training data and it achieves the overall performance and computational efficiency.

     

     

  • References

    1. [1] Martinez-Camara, E., Martin-Valdivia, M.T., Urena Lopez, & Montejo-Raez, A. (2014). Sentiment analysis in Twitter, Natural Language Engineering. 2014, vol. 20, pp. 1-28, 1.

      [2] Go, A., Bhayani, R., & Huang, L. (2009). Twitter sentiment classification using distant supervision. Stanford University, Stanford, USA, Tech. Rep. CS224N, 2009.

      [3] Martinez-Camara, E., Montejo-Raez, A., Martin-Valdivia, M.T., & Urena-Lopez, A. (2013). SINAI: Machine Learning and Emotion of the Crowd for Sentiment Analysis in Microblogs. Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013) pp. 402-407.

      [4] Zhang, L., Ghosh, R., Dekhil, M., Hsu, M., & Liu, B. (2011). Combining Lexicon-based and Learning-based Methods for Twitter Sentiment Analysis. Tech. Rep. HPL-2011-89, 06 2011.

      [5] Jiang, L., Yu, M., Zhou, M., Liu, X., & Zhao, T. (2011). Target-dependent Twitter sentiment classification, in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. vol. 1. Association for Computational Linguistics, 2011, pp. 151-160.

      [6] Perez-Rosas, V., Banea, C., & Mihalcea, R. (2012). Learning Sentiment Lexicons in Spanish. Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12).

      [7] Trivedi, R.S., & Eisenstein, J. (2013). Discourse Connectors for Latent Subjectivity in Sentiment Analysis. HLT-NAACL, 2013, pp. 808-813.

      [8] Polanyi, L. & Zaenen, A. (2004). Contextual Lexical Valence Shifters. Proceedings of the (AAAI) Spring Symposium on Exploring Attitude and Affect in Text: Theories and Applications, 2004.

      [9] Wilson, T., Wiebe, J., & Hoffmann, P. (2005). Recognizing contextual polarity in phrase-level sentiment analysis, in Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing. USA: Association for Computational Linguistics, 2005, pp. 347-191.

      [10] Jia, L., Yu, C., & Meng, W. (2009). The Effect of Negation on Sentiment Analysis and Retrieval Effectiveness. Proceedings of the 18th ACM Conference on Information and Knowledge Management, ser. CIKM 09. New York, NY, USA: ACM, 2009, pp. 1827-1830.

      [11] Severyn, A., & Moschitti, A. (2015). Twitter sentiment analysis with deep convolutional neural networks. Proc. 38th Int. ACMSIGIR Conf. Res. Develop. Inf. Retrieval, 2015, pp. 959-962.

      [12] Cambria, E., & White, B. (2014). Jumping NLP curves: A review of natural language processing research. IEEE Comput. Intell. Mag., vol. 9, no. 2, pp. 48-57, May 2014.

      [13] Cambria, E. (2016). Affective computing and sentiment analysis. IEEE Intell. Syst., vol. 31, no. 2, pp. 102-107, Mar./Apr. 2016.

      [14] Chen, Z., Liu, & B., Abdullah, R. (2016). Developing conceptual governance model for collaborative knowledge management system in public sector organisation. Journal of Information & Communication Technology (JICT), 15, 171-191.

      [15] Gimpel, K. (2011). Part-of-speech tagging for Twitter: Annotation, features, and experiments. J Proc. 49th Annu. Meet. Assoc. Comput. Linguistics: Short Papers, 2011, pp. 42-47.

  • Downloads

  • How to Cite

    Akilandeswari, P., Harshita, R., & KO.M, S. (2018). Sentiment Analysis using Machine Learning through Twitter Streaming API. International Journal of Engineering & Technology, 7(3.12), 1168-1174. https://doi.org/10.14419/ijet.v7i3.12.17781