Twitter Sentiment Tracking for Predicting Marketing Trends - Smart Information Systems: Computational Intelligence for Real-Life Applications - page 71

observed that in 11 out of 17 cities, the percentage of positive tweets on Microsoft
increased on August 24.
2.5.2 Future Works
As future works, the number of training dataset could be increased. This will pave
the way for performance-enhancing results, particularly for the Naïve Bayes classi-
fication. The preprocessing step can be further developed. To illustrate, emoticons
can be used for sentiment analysis. For example, an emoticon for smiling could be
placed with SMILE or “hahaha” can be altered to LAUGH. On the other hand, the
Support Vector Machine method might be another method in addition to the Naïve
Bayes and Maximum Entropy classifier methods. Furthermore, the tracking process
may not be confined to in days. With a longer tracking period, a better and more
effective data mining can be implemented. This system can be also modified in order
to monitor the views of the electors on the candidates in the elections in each city.
Or, how a person, institution, or opinion is perceived in different parts of the world
can be tracked with a modified version of the system.
Acknowledgments The first author has been funded by the Ministry of National Education,
Republic of Turkey.
References
1. K.M. Al-Aidaroos, A.A. Bakar, Z. Othman, Medical data classification with Naive Bayes
approach. Inf. Technol. J. 11 (9), 1166-1174 (2012)
2. D. Allard, D. D'Or, R. Froidevaux, An efficient maximum entropy approach for categorical
variable prediction. Eur. J. Soil Sci. 62 (3), 381-393 (2011)
3. S. Asur, B.A. Huberman, Predicting the future with social media, in 2010 IEEE/WIC/ACM
International Conference on Web Intelligence and Intelligent Agent Technology ( WI-IAT ), vol.
1 pp.492-499 (2010)
4. F. Benamara, C. Cesarano, A. Picariello, D.R. Recupero, V.S. Subrahmanian, Sentiment analy-
sis: adjectives and adverbs are better than adjectives alone, in ICWSM (2007)
5. A.L. Berger, V.J. Della Pietra, S.A. Della Pietra, A maximum entropy approach to natural
language processing. Comput. Linguist. 22 (1), 39-71 (1996)
6. E. Boiy, P. Hens, K. Deschacht, M.-F. Moens, Automatic sentiment analysis in on-line text, in
ELPUB , pp. 349-360 (2007)
7. J. Bollen, H. Mao, X. Zeng, Twitter mood predicts the stock market. J. Comput. Sci. 2 (1), 1-8
(2011)
8. J. Chen, H. Huang, S. Tian, Feature selection for text classification with Naive Bayes. Expert
Syst. Appl. 36 (3), 5432-5435 (2009)
9. A. Devitt, K. Ahmad, Sentiment polarity identification in financial news: a cohesion-based
approach, in Proceedings of the 45th Annual Meeting of the Association of Computational
Linguistics (2007)