Abstract
The increasing popularity of Twitter allows users to share target information as well as to express their own opinions on concerned subjects. Though the Twitter based information gathering techniques enable collecting direct responses from the target audience, not much by the way of research has been done to predict, model and forecast user behavior using the already existing and often abundant supply of personal data housed by the social network. This ready and continuous stream of social media information could be analyzed with the use of an Unsupervised learning technique to predict social behavior. In this research work, a novel fuzzy based hybrid hierarchical clustering model has been proposed to analyze Unsupervised techniques on Twitter samples. The efficiency of the model was measured based on the performance metrics namely accuracy, precision and recall. The model not only provides higher quality of results for dynamic users and tweet sentiment analysts, but also improves the performance of the clustering techniques in terms of accuracy with approximately 79.8%.
This is a preview of subscription content, log in via an institution to check access.
References
Rokach, L., Maimon, O.: Clustering methods. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 321–352. Springer, US (2005)
Jotheeswaram, J., Kumaraswamy, Y.S.: Opinion mining using decision tree based feature selection through Manhattan hierarchical technology. J. Theor. Appl. Inf. Technol. 58(1), 72–79 (2013)
Bharadwaj, B.: Text mining, its utilities, challenges and clustering techniques. Int. J. Comput. Appl. 135(7), 22–24 (2016)
Unnisa, M., Ameen, A., Raziuddin, S.: Opinion mining on Twitter data using unsupervised learning technique clustering. Int. J. Comput. Appl. 148(12), 12–19 (2016)
Sneha, G., Vidhya, C.T.: Algorithm for opinion mining and sentiment analysis: an overview. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 455–459 (2016)
Sarkar, A., Gonzallez, G.: DiegoLab 16 at SemEval-2016 task 4: sentiment analysis in Twitter centroids, clusters and sentiment lexicons. In: Proceedings of SemEval-2016, pp. 214–219 (2016)
Gutierrez Batista, K., Campana, J.R., Martinez-Folgoso, S., Vila, M.A: About the effects of sentiments on topic detection in social networks. In: European Hand Book of Crowd Sourced Geographic Information, pp. 224–235 (2015)
Stojanovski, D., Chorbev, I., Dimitrovski, I., Madjarov, G.: Social networks VGI: Twitter sentiment analysis of social hotspots. Procedia Comput. Sci. 183–190 (2015). Elsevier
Singh, P.K., Husain, M.S.: Methodological study of opinion mining and sentiment analysis techniques. Int. J. Soft Comput. 5, 1586–1592 (2014)
Li, G., Liu, F.: Sentiment analysis based on clustering: a framework in improving accuracy and recognizing neutral opinions. Appl. Intell. 40, 441–452 (2014). Springer
Coletta, L.F.S., da Silva, N.F.F., Hruschka, E.R., Hruschka, E.R.: Combining classification and clustering for tweet sentiment analysis, pp. 210–215. IEEE (2014)
Balcon, M.F., Liang, Y., Gupta, P.: Robust hierarchical clustering. J. Mach. Learn. Res. 4011–4051 (2014)
Soni, R., Mathai, K.J.: Improved Twitter sentiment prediction through cluster then predict model. Int. J. Comput. Sci. Netw. 559–563 (2015)
Cambaria, E., Poria, S., Bajpai, R., Schuller, B.: SenticNet 4: a semantic resource for sentiment analysis based on conceptual primitives. In: Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016), pp. 2666–2677, December 2016
Stojanovski, D., Chorbev, I., Dimitrovski, I., Madjarov, G.: Social networks VGI: Twitter sentiment analysis of social hotspots. In: Capiner, C., Haklay, M., Huang, H., Antoniou, V., Kettunen, J., Ostermann, F., Purves, R. (eds.) European Handbook of Crowd Sourced Geographic Information, pp. 223–235 (2016)
Lulla, S., Bhatia, V., Hemwani, R., Bhatia, G.: Social media analytics for E-commerce organization. Int. J. Comput. Sci. Inf. Technol. 7(6), 2431–2435 (2016)
Chifu, E.S., Letia, T.S., Chifu, V.R.: Un-supervised aspect level sentiment analysis using ant clustering and self organizing maps. In: IEEE International Conference on Speech Technology and Human Computer Dialogue (2015)
Ndene, L., Jouandeau, N., Akdag, H.: Importance of the neutral category in fuzzy clustering of sentiments. Int. J. Fuzzy Log. Syst. 4, 1–6 (2014)
Kirsci, M.: Integrated and differentiated spaces of triangular fuzzy numbers. Math. Subj. classif. 1–14 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Suresh, H., Gladston Raj, S. (2017). A Fuzzy Based Hybrid Hierarchical Clustering Model for Twitter Sentiment Analysis. In: Mandal, J., Dutta, P., Mukhopadhyay, S. (eds) Computational Intelligence, Communications, and Business Analytics. CICBA 2017. Communications in Computer and Information Science, vol 776. Springer, Singapore. https://doi.org/10.1007/978-981-10-6430-2_30
Download citation
DOI: https://doi.org/10.1007/978-981-10-6430-2_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6429-6
Online ISBN: 978-981-10-6430-2
eBook Packages: Computer ScienceComputer Science (R0)