Development of multilingual social media data corpus for sentiment classification

Rumaisa, Fitrah and Basiron, Halizah and Saaya, Zurina (2019) Development of multilingual social media data corpus for sentiment classification. Journal of Advanced Research in Dynamical and Control Systems, 11 (3). 286 - 293. ISSN 1943-023X

Text ARTICLE-FITRAH-JARDCS.PDF Restricted to Registered users only Download (209kB)

Abstract

The purpose of this study is to develop a corpus, which consists of 2 (two) languages: Bahasa Indonesia and Bahasa Melayu. In both languages, there are several similar vocabularies but have different meanings. The data used on this corpus, taken from social media that is Twitter and Facebook. Each language has 2100 words collected. After manual selection of words, there are 300 vocabularies that have different meanings. The words will be formed into the core of the formed corpus, regardless of the remaining words. This corpus will density on the polarity of each word per language type using automatic-annotation. So that will be formed two corpuses namely Bahasa Indonesia and Bahasa Melayu. This Corpus will be used in subsequent research on sentence-level annotation and demonstrated using manual annotations using human annotators.

Item Type:	Article
Uncontrolled Keywords:	Automatic-annotation, Bahasa Indonesia, Bahasa Melayu, Corpus, Facebook, Twitter
Divisions:	Faculty of Information and Communication Technology
Depositing User:	Sabariah Ismail
Date Deposited:	07 Dec 2020 10:28
Last Modified:	12 Jul 2023 11:24
URI:	http://eprints.utem.edu.my/id/eprint/24479
Statistic Details:	View Download Statistic

Actions (login required)

View Item