Sentiment Analysis System of Thai Video on Social Media Using Support Vector Machine
Article Sidebar
Main Article Content
Abstract
This research developed a system for analyzing Thai videos published on social media based on sentimental analysis method. It deployed a technique called support vector machine to provide guideline for customers to make decision on their goods purchase. It also provides guideline for business enterprise to manage enterprise information regarding videos on social media both positive and negative perspectives based on machine learning technique. First, this system extracts a dialog from video and featured it to text by using a technique called Term Frequency-Inversed Document Frequency (TF-IDF). Then, each text will processed by using a technique called Support Vector Machine (SVM) to attain the result. Experimental survey shows that this system achieved 98% of accuracy compared with 15 experts. It gained 4.79 of satisfaction with 0.41 of Standard Deviation from 60 users. Finally, It is apparently shown that this system: Sentiment Analysis System of Thai Video on Social Media Using Support Vector Machine is capable of analyzing sentiment from Thai videos at very high efficiency.
Article Details
Copyright of all articles published is owned by CRMA Journal.
References
สุพัตรา วิริยะวิสุทธิสกุบ, (2559). ระบบแจ้งเตือนโซเซียลมีเดียไทยสำหรับธุรกิจด้วยซัพพอร์ทเวกเตอร์แมชชีน. วารสารปัญญาภิวัฒน์, 8 : 223-233.
Neethu M.S., and Rajasree R., (2013). Sentiment Analysis in Twitter using Machine Learning Techniques, International Conference Computing, communications and Networking Technologies (ICCCNT), 4-6July 2013.
Lima A.C.E.S. and Castro deL.N., (2013). Automatic sentiment analysis of Twitter messages, Forth International Conference on Computational Aspects of Social Networks, 52-57.
Isah H., Neagu D. and Trundle P., (2014). Social Media Analysis for Product Safety Using Text Mining and Sentiment Analysis, 14th UK Workshop on Computational Intelligence, 19 June 2015.
Kadmateekarun, P. and Nuanmeesri, S., (2015) Automatic sentiment analysis from opinion of Thais speech audio, International Conference on Science and Technology (TICST), 25-26 May 2015.
Naradhipa, A. R. and Purwarianti, A., (2011). Sentiment classification for Indonesian message in social media, In Proceedings of the 2011 International Conference on Electrical Engineering and Informatics (IEEE), 1-4.
Haji H. Binali ; Chen Wu ; and Vidyasagar Potdar, (2009). A new significant area: Emotion detection in E-learning using opinion mining techniques, International Conference on Digital Ecosystems and Technologies, (IEEE. DEST '09), 1-3 June 2009.
Rosas, V.P., Mihalcea, R., and Morency, L.-P., (2013). Multimodal Sentiment Analysis of Spanish Online Videos, IEEE Intelligent Systems.
Pongthanoo P., al et., (2012). Customer Satisfaction analysis from comment text using text using opinion mining, International conference on Knowledge and Smart Technologies (KST-2012), 7-8 July 2012, 53-60.
Akaichi J., Dhouioui Z., and Perez M.J.L.H., (2013). Text mining facebook status updates for sentiment classification, International Conference on System Theory, Control and Computing (ICSTCC 17th), 11-13 October 2013.
Kaushik L., Sangwan A. and Hansen J.H.L., (2013). Sentiment extraction from natural audio streams, International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP 2013), 26-31 May 2013. 8485-8489.
อดิเทพ ไชยสาร และ รัฐสิทธิ์ สุขะหุต, (2013). การประมาณอารมณ์จากความคิดเห็นภาษาไทยโดยใช้เทคนิคการเรียนรู้ของ เครื่อง, The 9th National Conference on Computing and Information Technology, 9-10 May 2013, 260-266.
Brynielsson J., and et al., (2014). Emotion classification of social media posts for estimating people’s reactions to communicated alert messages during crises. Security Informatics, 3(1).
Sarakit, P., et al., (2015). Classifying emotion in Thai youtube comments. International Conference of Information and Communication Technology for Embedded Systems (6th IC-ICTES IEEE), 1-5).
นิเวศ จิระวิชิตชัย, ปริญญา สงวนสัตย์ และพยุง มีสัจ. (2011). การพัฒนาประสิทธิภาพการจัดหมวดหมู่เอกสารภาษาไทยแบบอัตโนมัติ, วารสารพัฒนบริหารศาสตร์, 51(3): 188-205.
Thai Split Library : THsplitlib 3.0 [Computer software]. Retrieved from http://www.alogik.com/thsplitlib/
Viriyavisuthisakul S., et al., (2015). A comparison of similarity measures for online social media Thai text classification. International Conference on Electrical Engineering/Electronics, Computer Telecommunications and Information Technology (12th ECTI-CON IEEE), 1-6.
ราตรี นันทสุคนธ์, (2554). การวิจัยในชั้นเรียนและการวิจัยพัฒนาการเรียนการสอน, กรุงเทพฯ: จุดทอง จำกัด.