Role of Text Mining in Extracting Valuable Information from Text Data

Zatul Alwani Shaffiei; Amir Syafiq Syamin Syah Amir Hamzah; Shaikh Mariyam Harunor Rashid; Naoki Oshima

doi:10.37934/araset.32.1.263271

Authors

Zatul Alwani Shaffiei Department of Electronic Systems Engineering (ESE), Malaysia–Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
Amir Syafiq Syamin Syah Amir Hamzah Department of Management of Technology (MoT), Malaysia–Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
Shaikh Mariyam Harunor Rashid Department of Electronic Systems Engineering (ESE), Malaysia–Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
Naoki Oshima Graduate School of Management of Innovation and Technology, Yamaguchi University, Japan

DOI:

https://doi.org/10.37934/araset.32.1.263271

Keywords:

Text mining, Word cloud, Dendrogram, Co-occurrence network, Euclidean distance

Abstract

Text mining has become a popular field with the rapid development of information technology and the extensive amounts of unstructured text data such as web pages, social network sites and technical documentations. This data contains a lot of information, which is extremely difficult to deal with the huge number and various forms. Extracting and analysing important information from massive data for example in automotive industries has become our major problem. The main aim of text mining is to extract important information from massive text data that are difficult to be handled manually with error-free. In this paper, the fundamental concept is based on Euclidean distance in finding the similarity between words. Finally, a set of data is used to describe the similarities, distances and frequencies between several words. Word cloud, bar plot, dendrogram and co-occurrence network are also presented to illustrate the behaviour of the text data.