Logo IPI  
Journal > Journal of ICT Research and Applications > Social Media Text Classification by Enhancing Well-Formed Text Trained Model

 

Full Text PDF (1,134 kb)
Journal of ICT Research and Applications
Vol 10, No 2 (2016)
Social Media Text Classification by Enhancing Well-Formed Text Trained Model
Jotikabukkana, Phat ( School of ICT, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani,)
Sornlertlamvanich, Virach ( School of ICT, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani,)
Manabu, Okumura ( Tokyo Institute of Technology, Ookayama Campus, Ookayama Meguro-ku, Tokyo,)
Haruechaiyasak, Choochart ( National Electronics and Computer Technology Center, Thailand Science Park, Pathum Thani)
Article Info   ABSTRACT
Published date:
31 Aug 2016
 
Social media are a powerful communication tool in our era of digital information. The large amount of user-generated data is a useful novel source of data, even though it is not easy to extract the treasures from this vast and noisy trove. Since classification is an important part of text mining, many techniques have been proposed to classify this kind of information. We developed an effective technique of social media text classification by semi-supervised learning utilizing an online news source consisting of well-formed text. The computer first automatically extracts news categories, well-categorized by publishers, as classes for topic classification. A bag of words taken from news articles provides the initial keywords related to their category in the form of word vectors. The principal task is to retrieve a set of new productive keywords. Term Frequency-Inverse Document Frequency weighting (TF-IDF) and Word Article Matrix (WAM) are used as main methods. A modification of WAM is recomputed until it becomes the most effective model for social media text classification. The key success factor was enhancing our model with effective keywords from social media. A promising result of 99.50% accuracy was achieved, with more than 98.5% of Precision, Recall, and F-measure after updating the model three times.
Copyrights © 2016