Topic Modeling on Indonesian Online Shop Chat

Abstract

This paper aims to discover topics from an Indonesian online shop chat. Moreover, we employed Latent Dirichlet Allocation to find out what kind of topics that are often discussed and conversation trends between buyers and customer service. Several tasks were performed, such as, collecting data, preprocessing, phrase aggregation, topic modeling, and topic analysis. We found several attracting findings during our experiments. In preprocessing task, product name extraction from URLs assisted to discover the intended product from the customer's conversation. On the other hand, the phrase aggregation task helped us to merge various terms which have same intended meaning, so that, we could obtain better topical model result and easier to determine the topic label.