1. UKM Learning and Research Repository
2. Master Thesis / Tesis Master
3. Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Title:	Malay sentiment classification based on machine learning and lexicon based approach
Authors:	Ahmed Ali Mohammed Al-Saffar (P72233)
Supervisor:	Nazlia Omar, Prof. Madya Dr.
Keywords:	Semantic computing Computational linguistics Malay language -- Data processing Universiti Kebangsaan Malaysia -- Dissertations Dissertations, Academic -- Malaysia
Issue Date:	14-Jul-2015
Description:	Sentiment analysis or opinion mining is a field that analyses people's opinions towards entities such as products and organizations. Although many studies that focus on sentiment analysis have been conducted, there remains a limited amount of studies that focus on sentiment analysis in the Malay language. Malay sentiment analysis is difficult due to the nature of Malay language which consists of many synonyms and also due to the limitation of available language resources in Malay. This research aims to propose a model for Malay sentiment classification based on selecting the best probabilistic classifier. This study proposes a new set of features, in conjunction with previously proposed features, to capture sentiment features in documents. A Malay sentiment lexicon is used for this purpose. The features values are fed to train three machine learning based classifiers, namely Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbour (KNN). A voting algorithm is used to integrate the overall strength of the three classifiers. For the experiments, 2000 reviews written in the Malay language in the movie domain are used. The results show that the combined classifiers, used in conjunction with the lexicon-based method, obtained an accuracy of 93.50% and outperformed the baseline. This shows that the proposed model is viable for the Malay sentiment classification tasks.,Master of Information Technology
Pages:	92
Call Number:	QA76.5913.S236 2015 3 tesis
Publisher:	UKM, Bangi
Appears in Collections:	Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.