Analysis of Thai Phrases Effecting Opinion Classification
Article Sidebar
Main Article Content
Abstract
This research aims to analyze Thai phrases effecting opinion classification. Most opinions in Thai are phrases. Customer reviews or opinions can be screened according to the word type that affects the efficiency of the classification. Thus, analyzing the different types of words from customer opinions about restaurants is a challenging research. The 4,487 messages were obtained from wongnai.com website. The different types of words include nouns, verbs, adverbs, nouns and verbs, nouns and adverbs, verbs and adverbs, and nouns verbs and adverbs. Naïve Bayes (NB), Support Vector Machine (SVM), C4.5, K-Nearest Neighbor (KNN), Random Forest (RF) and Multi-layer Perceptron (MLP) techniques were used to create classification models. 10-fold cross validation was used to divide the data into learning and testing sets. Accuracy, precision, and recall were employed to measure the effectiveness of the techniques. The experimental results showed that the Naïve Bayes model had the best result when using nouns, verbs and adverbs data which had an accuracy up to 89.08%, precision up to 89.12% and recall up to 89.10%.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in Journal of Industrial Technology Ubon Ratchathani Rajabhat University both hard copy and electronically are belonged to the Journal.
References
Wutthithamkhun B. The social media restaurant reviews and the decision making in choosing restaurant in Bangkok. Bangkok University. 2017.
Malik M. Habib S. Agarwal P. A Novel Approach to Web-Based Review Analysis Using Opinion Mining. Procedia Computer Science. 2018; 132: 1202-09.
Thadmuang R. Chirawichitchai N. Thai sentiment analysis of product review online using vector machine support algorithms. Engineering Journal of Siam University. 2017; 18(1): 1-12
Pinmuang N. Thongkam J. Classifying Thai opinions on online media using text mining. Science and Technology Journal. Mahasarakham University. 2018; 37: 372-9.
Shah FP. Patel V. A review on feature selection and feature extraction for text classification. 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET); 2016. 23-25 March 2016.
Phopli W. Boonmatham S. Meesad P. Ensemble Feature Selection for Sparse Data. The Thirteenth National Conference on Computing and Information Technology; 2017. p. 373-8.
Haruechaiyasak C. Jitkrittum W. Sangkeettrakarn C. Damrongrat C. Implementing News Article Category Browsing Based on Text Categorization Technique. 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology; 2008. p. 9-12 Dec. 2008.
Nuipian V. Meesad P. A Comparison of Filter and Wrapper Approaches with Text Mining for Text Classification. The Journal of Industrial Technology. 2013; 9(3): 118-29.
Pukkhem N. Junmanee C. Ouisui S. Automatic Thai Folk Wisdom Classification using Data Mining Approach. Thaksin University Journal. 2017; 20(3): 300-07.
Samal B. Behera AK. Panda M. Performance analysis of supervised machine learning techniques for sentiment analysis. International Conference on Sensing, Signal Processing and Security; 2017.
Kongthon A. Haruechaiyasak C. Pailai J. Kongyoung S. The role of Twitter during a natural disaster: Case study of 2011 Thai Flood. PICMET:Technology Management for Emerging Technologies; 2012.
Hossain FMT. Hossain MI. Nawshin S. Machine learning based class level prediction of restaurant reviews. IEEE Region 10 Humanitarian Technology Conference; 2017.
Breiman L. Random Forests. Machine Learning. 2001; 45(1): 5-32.
Xu X. Cao D. Zhou Y. Gao J. Application of neural network algorithm in fault diagnosis of mechanical intelligence. Mechanical Systems and Signal Processing. 2020; 141: 1-13.
