International Journal of Intelligent Systems and Applications(IJISA)

ISSN: 2074-904X (Print), ISSN: 2074-9058 (Online)

Published By: MECS Press

IJISA Vol.6, No.9, Aug. 2014

Emotion Detection of Tweets in Indonesian Language using Non-Negative Matrix Factorization

Full Text (PDF, 524KB), PP.54-61

Views:186   Downloads:4


Agus Zainal Arifin, Yuita Arum Sari,Evy Kamilah Ratnasari, Siti Mutrofin

Index Terms

Emotion Detection, Tweet, Indonesian Language, Emoji, Emoticon, Hashtag, Wordnet-Affect, NMF


Emotion detection is an application that is widely used in social media for industrial environment, health, and security problems. Twitter is ashort text messageknown as tweet. Based on content and purposes, the tweet can describes as information about a user’s emotion. Emotion detection by means oftweet, is a challenging problem because only a few features can be extracted. Getting features related to emotion is important at the first phase of extraction, so the appropriate features such as a hashtag, emoji, emoticon, and adjective terms are needed. We propose a new method for analyzing the linkages among features and reducedsemantically using Non-Negative Matrix Factorization (NMF). The dataset is taken from a Twitter application using Indonesian language with normalization of informal terms in advance. There are 764 tweets in corpus which have five emotions, i.e. happy (senang), angry (marah), fear (takut), sad (sedih), and surprise(terkejut). Then, the percentage of user’s emotion is computed by k-Nearest Neighbor(kNN) approach. Our proposed model achieves the problem of emotion detectionwhich is proved by the result near ground truth.

Cite This Paper

Agus Zainal Arifin, Yuita Arum Sari,Evy Kamilah Ratnasari, Siti Mutrofin,"Emotion Detection of Tweets in Indonesian Language using Non-Negative Matrix Factorization", International Journal of Intelligent Systems and Applications(IJISA), vol.6, no.9, pp.54-61, 2014. DOI: 10.5815/ijisa.2014.09.07


[1]F. Atefeh, W. Khreich. A Survey of Techniques for Event Detection in Twitter. Computational Intelligence, September, 2013.

[2]S. M. Mohammad. #Emotional Tweets. Proceedings of the SemEval12, 2012, 1.

[3]W. Wang, L. Chen, K. Thirunarayan et al. Harnessing Twitter ‘Big Data’ for Automatic Emotion Identification. Proceedings of SocialCom12, 2012, pp. 587-592.

[4]M. Purver,S. Battersby. Experimenting with Distant Supervision for Emotion Classification. Proceedings of EACL ’12,2012, pp. 482-491.

[5]Z. Yuan,M. Purver. Predicting Emotion Label for Chinese Microblog Texts. Proceedings of SDAD 2012,2012, pp.40.

[6]A. Neviarouskaya, H. Predinger, M. Ishizuka. Textual Affect Sensing for Sociable and Expressive Online Communication. Proceedings of ACII’07, 2007, pp. 218-229.

[7]Arifin, K. E. Purnama. Classification of Emotions in Indonesian Texts Using K-NN Method. International Journal of Information and Electronics Engineering, v2, n6, 2012, pp.899-903. 

[8]J. Suttles, N. Ide. Distant supervision for emotion classification with discrete binary values. Computational Linguistics and Intelligent Text Processing, 2013, pp.121-136.

[9]J. Asian, H. E. Wiliams, S. M. M. Tahaghoghi. Stemming Indonesian. Proceedings of ACSC’05, v38, 2005, 307-314.

[10]A. Z. Arifin, R. Darwanto, D. A. Navastara, H. T. Ciptaningtyas. Klasifikasi Online Dokumen Berita Dengan Menggunakan Algoritma Suffix Tree Clustering. Proceeding of SESINDO2008, 2008, 17.

[11]A. Z. Arifin, I. P. A. K. Mahendra, H. T. Ciptaningtyas. Enhanced confix stripping stemmer and ants algorithm for classifying news document in indonesian language. Proceeding of ICTS, 2009.

[12]X. Yan, J. Guo, S. Liu et al. Learning topics in short texts by non-negative matrix factorization on term correlation matrix. Proceedings of SDM13, 2013.

[13]A. Z. Arifin. Penggunaan Digital Tree Hibrida pada Aplikasi Information Retrieval untuk Dokumen Berita. Proseding Seminar Nasional Sains dan Teknologi, 2002.

[14]P. C. Barman, N. Iqbal, S. Y. Lee.Non-negative Matrix Factorization Based Text Mining: Feature Extraction and Classification. Neural Information Processing, 2006, pp. 703-712.

[15]M. M. Rahman. Mining Social Data to Extract Intellectual Knowledge. IJISA, v4, n10, 2012, pp.15-24.

[16]A. Z. Arifin, A. Rachmania, I. Lukmana. Topic Identification of Indonesian Language News Article Based on Theme Query. IPTEK, v1, n1, 2013.