Implementation of Textrank Algorithm in Product Review Summarization

Abstract

Internet technology led to the emergence of Web 2.0 which increase the number of User Generated Content (UGC) on the network. Online product review is a form of UGC. The case study in this research is a review of handphone products. The large number of reviews will take long time to read and compare between existing product reviews, so we need a technique that online product review can be read quickly without losing of its important information. The technique that can be used is the text summarizing technique. Text summarization techniques produce simplified versions of texts. In general, text summarization can be divided into two types, namely extractive and abstractive summaries. This research used extractive summaries. One important component in the process of obtaining an extractive summary is sentence extraction. In this study, the algorithm used for sentence extraction is TextRank. The purpose of this study was to determine the performance of the TextRank algorithm with handphone product reviews data by implementing it in different data conditions based on the presence or absence of a stopword and typo. These data conditions are used to formulate test scenarios. Testing is done by calculating the Rouge-1 value which compares the summary of system and experts. Expert who involved in this study are 2. Expert 1 is a person with expertise in Indonesian and Expert 2 is someone who has the knowledge and understanding of mobile phones with various types and characteristics. From the test results obtained, Expert 1 gets the best results for scenario 2 where data conditions are there is typo and no stopword with an average value of Rouge-1 of 42.29% and Expert 2 gets the best results for scenario 3 where data conditions are no typo and there is stopword with an average value of Rouge-1 is 46.71%. The results shows that the TextRank algorithm is not able to produce a good summary for handphone product review dataset.