K-medoids algorithm on Indonesian Twitter feeds for clustering trending issue as important terms in news summarization

News summary could be a solution for information access need. However, it is challenging because of the number of news is growth rapidly. The information integration of several news has some difficulties because sentences that compose news summary could be come from various issues. Short text or Twitter Feeds called tweets could be used to recognize those issues. More weight value are given to the issue terms. Hence, the issue terms will exists within the news summary. This paper focuses on the usage of K-Medoids algorithm for tweet clustering. The data in this study is Twitter feeds in Indonesian. The result experiment shows the effect of re-tweet occurrences and also its influence in the summary result.