Named Entity Recognition using Fuzzy C-Means Clustering Method for Malay Textual Data Analysis

Abstract

The Named Entity Recognition (NER) task is among the important tasks in analysing unstructured textual data as a solution to gain important and valuable information from the text document. This task is very useful in Natural Language Processing (NLP) to analyse various languages with distinctive styles of writing, characteristics and word structures. The social media act as the primary source where most information and unstructured textual data are obtained through these sources. In this paper, unstructured textual data were analysed through NER task focusing on the Malay language. The analysis was implemented to investigate the impact of text features transformation set used for recognising entities from unstructured Malay textual data using fuzzy c-means method. It focuses on using Bernama Malay news as a dataset through several steps for the experiment namely pre-processing, text features transformation, experimental and evaluation steps. As a conclusion, the overall percentage accuracy gave markedly good results based on clustering matching with 98.57%. This accuracy was derived from the precision and recall evaluation of both classes. The precision result for NON_ENTITY class is 98.39% with 100.00% recall, whereas for an ENTITY class, the precision and recall are 100.00% and 88.97%, respectively.