The Effect of Brill Tagger on The Classification Results of Sentiment Analysis Using Multinomial Naïve Bayes Algorithm

Astero Nandito, Abdiansah Abdiansah, Novi Yusliani

Abstract

Twitter is a good indicator for influence in research, the problem that
arises in research in the field of sentiment analysis is the large number
of factors such as the use of informal or colloquial language and other
factors that can affect the results of sentiment classification. To
improve the results of sentiment classification, an information
extraction process can be carried out. One part of the information
extraction feature is a part of speech tagging, which is the giving of
word classes automatically. The results of part of speech tagging are
used for weighting words based on part of speech. This study
examines the effect of Part of Speech Tagging with the method Brill
Tagger in sentiment analysis using the Naive Bayes Multinomial
algorithm. Testing were carried out on 500 twitter tweet texts and
obtained the results of the sentiment classification with implementing
part of speech tagging precision by 73,2%, recall by 63,2%, f-measure
by 67,6%, accuracy by 60,7% and without implementing part of
speech tagging precision by 65,2%, recall by 60,6%, f-measure by
62,4% accuracy by 53,3%. From the results of the accuracy obtained,
it shows that the application of part of speech tagging in sentiment
analysis using the Multinomial Naïve Bayes algorithm has an effect
with an increase in classification performance.

Full Text:

PDF

References

Amrullah, A. Z., Hartanto, R., & Mustika, I. W. (2017). A comparison of different part-of-speech tagging technique for text in Bahasa Indonesia. Proceedings - 2017 7th International Annual Engineering Seminar, InAES 2017.

Aprillia (2018). “Pengaruh Parf Of Speech Tagging dalam Analisis Sentimen menggunakan Algoritma Multinomial Naïve Bayes.” Skripsi Jurusan Teknik Informatika, Fak. Ilmu Komputer, UNSRI – Tidak diterbitkan.

Hamzah, A., & Widyastuti, N. (2015). Document subjectivity and target detection in opinion mining using HMM POS-Tagger. Proceedings of 2015 International Conference on Information and Communication Technology and Systems, ICTS 2015, September 2015, 83–87.

McCallum, A., & Nigam, K. (1998). A Comparison of Event Models for Naive Bayes Text .Classification. 58(8), 582–591.

Muljono, Afini, U., Supriyanto, C., & Nugroho, R. A. (2017). The development of Indonesian POS-Tagging system for computer-aided independent language learning. International Journal of Emerging Technologies in Learning, 12(11), 138–150.6.

Setyaningsih, E. R. (2017). Part of Speech Tagger Untuk Bahasa Indonesia Dengan Menggunakan Modifikasi Brill. Dinamika Teknologi, 9(1), 37–42.

Song, J., Kim, K. T., Lee, B., Kim, S., & Youn, H. Y. (2017). A novel classification approach based on Naïve Bayes for Twitter sentiment analysis. KSII Transactions on Internet and Information Systems, 11(6), 2996–3011.

Winarko, E., & Putrianti, N. D. (2014). Analisis Sentimen Twitter untuk Teks Berbahasa Indonesia dengan Maximum Entropy dan Support Vector Machine. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 8(1), 91–100.

Xu, R. (2014). POS weighted TF-IDF algorithm and its application for an MOOC search engine. ICALIP 2014-2014 International Conference on Audio, Language and Image Processing, Proceedings, 868–873.

DOI: https://doi.org/10.36706/sjia.v2i1.17

Refbacks

  • There are currently no refbacks.