Sentiment analysis is process that contains text-based datasets which are positive, negative or neutral. Social media has provided a place for web users to express sharing of thoughts, opinions and convey news on different topics in an event. Haters in various media, including social media, can be punished. In the circular, stated that hate speech issue has been getting attention both national and international community concern for the protection of human rights (HAM). Classification of algorithms such as Naive Bayes (NB) and Particle Swarm Optimization (PSO) was proposed by many researchers to be used in the analysis of text sentiment. Naive Bayes’s algorithms and methods, will be tested with two inputs using tokenize and Transform Cases’s comments are positive (100 text comments) and negative (100 comments text), it obtained experimental results accuracy: 62.50 % +/- 7.50 % (micro : 62.50 %). The result will be increased if the results of the experiment combine with Particle Swarm Optimization (PSO), it obtained experimental results were better accuracy: +/- 74.00 % 7:68 % (micro : 74.00 %). The results showed that Naive Bayes (NB) will get the best results if it combined with Particle Swarm Optimization (PSO).
Keywords : sentiment analysis, internet ethics, social media, Naive Bayes, particle swarm optimization
Tesis Sopian Aji
Altheneyan, A. S. , Menai, M. E. B. (2014). Naı¨ve Bayes classifiers for authorship attribution of Arabic texts. Journal of King Saud University –Computer and Information Sciences, 473-484. doi.org/10.1016/j.jksuci.2014.06.006
Darmawan, Agus. (2015). Penerapan Model Support Vector Machine Text Mining Pada Komentar Review Smartphone Android Vs Blackberry Dengan Teknik Optimasi Genetic Algorithm. 100-115, ISSN: 1979-276X
Darujati, Cahyo. Gumelar, A., B., (2012) . Pemanfaatan Teknik Superviseduntuk Klasifikasi Teks Bahasa Indonesia. ISSN 1858-4667
Dehkharghani, R., Mercan, H., Javeed, A., & Saygin, Y. (2014). Sentimental causal rule discovery from Twitter. Expert Systems with Applications, 4950–4958. doi:10.1016/j.eswa.2014.02.024
Indrayuni, E., and Wahyudi, M., (2015). Penerapan Character N-Gram Untuk Sentiment Analysis Review Hotel Menggunakan Algoritma Naive Bayes. ISBN 978-602-72850-0-2
Kang, H., Yoo, S. J., & Han, D.(2012). Senti lexicon and improved Naïve Bayes algorithms for sentiment analysis of restaurant reviews. Expert Systems with Applications, 6000–6010. doi:10.1016/j.eswa.2011.11.107
Kontopoulos, E., Berberidis, C., Dergiades, T., & Bassiliades, N. (2013). Ontology-based sentiment analysis of twitter posts. Expert Systems with Applications, 40(10), 4065–4074. doi:10.1016/j.eswa.2013.01.001
Martinez, I. P., Sanchez, F. G., Garcia, R. V., Moreno, V., Fraga, A., Cervantez, J. L. S. (2014). Feature-based opinion mining through ontologies. Expert Systems with Applications, 5995-6008. doi:10.1016/j.eswa.2014.03.022
Park, T. S., Lee, J. H., & Choi, B. (2009). Optimization for Artificial Neural Network with Adaptive inertial weight of particle swarm optimization. Cognitive Informatics, IEEE International Conference , 481-485
Routray, P., Swain, C. K. & Mishra, S. P., 2013. A Survey on Sentiment Analysis. International Journal of Computer Applications, Agustus, pp. 1-8.
Tripathy, A., Agrawal, A., Rath, S. K. (2015). Classification of Sentimental Reviews Using Machine Learning Techniques. ScienceDirect, 57 ( 2015 ) 821 – 829. doi: 10.1016/j.procs.2015.07.523
Xhemali, D., J. Hinde, C. & G. Stone, R., 2009. Naïve Bayes vs. Decision Trees vs. Neural Networks in the Classification of Training Web Pages. International Journal of Computer Science Issues, pp. 16-23