APLIKASI OPINION MINING DAN SENTIMENT ANALYSIS UNTUK MERANCANG MESIN PENCARI OPINI PADA KUESENER MAHASISWA
DOI:
https://doi.org/10.34151/technoscientia.v9i1.143Keywords:
HMM POS_Tagger, opinion, classificationAbstract
The measurement of academic services using questionnaires with multiple choice answers generally provide comments and advice columns. In the data analysis results, comments and suggestions made by the thousands of students can not be utilitized due to the lack of analysis tools. Whereas comments and suggestions can actually contain student opinions on various things, such as facilities, faculty, library and others. Opinion mining and sentiment analysis as a new tool in text mining can be applied to the data to utilitize comments and suggestions. This research applied HMM-POS Tagger to give automatically POS TAG to the sentence based on training POS TAG data by using the Hidden Markov Model. By implementing POS TAG pattern the comments can then be determined whether it was opinion or not. Morever if it were opinion it can be determinied its target and also the orientation of the opinion whether it is positive or negative. The data used was 1,000 comments given POS-TAG manually and 1,000 comments as test data. Sentiment analysis is applied using four methods of classification, namely SVM, NBC, ME and KM-Clustering. The result showed that the accuracy of POS-Tagger was 0.95 and the avarage of accuracy of four classification method was 0.85.
References
Cortes,C. and Vapnik,V., 1995,"Support-Vector Networks", Machine Learning, 20, pp.273-297
Cutting, D., Kupiec,J., Pesderson,J. and Sibun,P., “A Practical Part-ofspeech Tagger, Xerox Palo Alto Research Center”, in Proceeding of the third Conference on applied Natural Language Processing , 1992, pp.133-140.
Greaves, F., D.R. Cano, C. Millet, A.Darzi, and L. Donaldson, “Use of Sentiment Analysis for Capturing Patient Experience From Free-Text Comments”, Journal of Medical Internet Research, 2013, 15:11, e239. Online publication date: 1-Jan-2013
Grimes, S., 2013, Unstructured Data and the 80 Precent Rule, Clarabridge Bridgepoints.
Liu,B.,2010, “Sentiment Analysis: Multi Facet Problem”, IEEE Intelligence System, 25 (3),pp:76-80
Loia, L. and Senatore, S.,”A fuzzy-oriented sentic analysis to capture the human emotion in Web-based content”, Knowledge-Based Systems 58, 2014, pp. 75-85 Online publication date: 1-Mar-2014
McCallum, A. and Nigam, K., 1998, "A Comparison of Event Models for Naive Bayes Text Classification", AAAI/ICML-98 Workshop on Learning for Text Categorization, pp. 41-48
Pang, B., Lee, L. and Vaithyanathan, S., 2002, Thumbs up?: sentiment classification using machine learning techniques", Proceeding EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10, pp: 79-86
Putten,P.V.D., Kok, J. and Gupta,A., 2002, Why the Information Explosion can be Bad for Data Mining, and How Data Fusion Provides a Way Out, Proc.of the 2nd SIAM International Conference on Data Mining,pp:11-13
Pisceldo. F., Manurung, R. and Adriani,M. “Probabilistic Part-of-Speech Tagging for Bahasa Indonesia”, Third International MALINDO Workshop, colocated event ACL-IJCNLP, Singapore, 2009
Shelke,N.M., Deshpande,S. and Thakre,V., “Survey of Techniques for Opinion Mining,” International Journal of Computer Applications (0975 – 8887) Volume 57– No.13, November 2012
Wicaksono, A.F. and Purwarianti,A., 2010, "HMM Based Part-of-Speech Tagger for Bahasa Indonesia", Proceedings of the 4th International MALINDO Workshop, Jakarta.
Widhiyanti, K and A. Harjoko, “POS Tagging for Bahasa Indonesia dengan HMM dan Rule Based”, INFORMATIKA Vol.8.,No.2., November 2012, pp.151-167
