Query Expansion Evaluation for Chatbot Application

Abstract

At this digital era, the recent stage of business system makes so many opportunity and innovation, such as online shopping. The system provides easier interaction between seller and customer. But the problem is, the seller can't response immediately while the customer asks. Therefore, a chatbot can be a solution so the seller can response a question quickly. This research proposes a chatbot system with a frequently asked question knowledge base. An additional query expansion mechanism based on thesaurus dictionary is implemented. Cosine similarity metric then being used to measure similary between query and question in frequently asked question. This research reveals the experimental results of this approach not as good as of similarity logic system.