Automatic summarization from Indonesian hashtag on twitter using TF-IDF and phrase reinforcement algorithm

Abstract

The objective of this research is to produce a summary about what is currently happening from Indonesian hashtag on Twitter. Combination of TF-IDF (term frequency-inverse document frequency) and Phrase Reinforcement Algorithm are used as the methodology to do the automatic summarization. We use 2 sentences as the final summary result. It contains all essential information given by Twitter data. At the end of this paper, we describe the evaluation result by analyzing result using Precision and ROUGE. Based on the result, we conclude that TF-IDF and Phrase Reinforcement Algorithm can successfully generate summary and it works well enough on hashtags that do not have such lot variants of the word. Generally, summary results quality is quite low because the data still contains too much noise. The precision is 0.327 and ROUGE-1 is 0.3087.