Clustering articles in bahasa Indonesia using self-organizing map

One of the text explosion in the Internet is the availability of any articles published by any institution at any time. As the articles are widely available in the Internet, there are many observations that can be done by utilizing the available articles. One of the basic things to do is categorizing the articles. As the number of the articles are massive, categorizing them manually is not an option. Therefore, we propose the self-organizing map (SOM) algorithm with the combination of Term Frequency - Inverse Document Frequency (TF-IDF) and multiword expressions to categorize articles in Bahasa Indonesia. This research clusters health articles into several topics according to keywords of each articles. The process is divided into three sections, such as text pre-processing, keywords extraction, and the implementation of self-organizing maps. Number of keywords that are used as parameters to self-organizing maps algorithm will influence the number of resulted clusters.