Chatbot-based Culinary Tourism Recommender System Using Named Entity Recognition

Abstract

Over the time, culinary tourism in several cities of Indonesia is growing rapidly, one example is culinary tourism in Bandung city. This makes it difficult for tourists to decide their choice. To overcome these problems, a recommendation system is needed. Thus, in this study we developed a chatbot-based conversational recommendation system to assist users in finding culinary tourism recommendations. The chatbot was built using Google Dialogflow platform and uses methods in Natural Language Processing, namely Named Entity Recognition. Named Entity Recognition was used to extract entities from user’s input, such as usernames and culinary preferences. To find culinary recommendations, TF-IDF and cosine similarity was used to find similarities between each culinary based on reviews, telegram was used as a medium to implement the chatbot that has been built. The chatbot has a good performance in providing culinary recommendations, it can be seen from the score obtained from usability testing on the recommendation aspect, which is 85.7%.