Lexical Based Approach For Analysing Sentiments In Malay Language On Social Media Platforms

Saaya, Zurina and Basiron, Halizah and Zakaria, Mohd Hafiz and Abdul Rahman, Ahmad Fadzli Nizam and Hassim, Nurulhalim (2017) Lexical Based Approach For Analysing Sentiments In Malay Language On Social Media Platforms. Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text Lexical Based Approach For Analysing Sentiments In Malay Language On Social Media Platforms.pdf - Submitted Version Restricted to Registered users only Download (493kB)

Abstract

Sentiment analysis is a method to determine whether the feedback given by the user is positive or negative. The comments posted by users consists noisy text which includes abbreviations, misspelling and short forms. Sentiment analysis becomes challenging when dealing with noisy data. The objective of this research is to introduce a lexical based method in classifying sentiment of Facebook comments in Malay language. Two types of lexical based techniques namely Term Counting and Term Counting Average are implemented in order to classify the sentiment of Facebook comments. Several parts of speech tags are being taken into account. Pre-processing process is involved in dealing noisy texts in data. Term Counting works better for adjectives and adverbs while Term Counting Average performs better for verbs and negation words.

Actions (login required)

View Item