Pengembangan Chatbot Rule-Based untuk Rekomendasi Wisata Berbasis Content-Based Filtering

Abstract

Tourism is a strategic sector in supporting regional economic growth, including in Takengon City, which has high potential in natural, cultural, and culinary tourism. However, limited access to structured and relevant tourism information often becomes an obstacle for tourists in selecting destinations that match their preferences. This study aims to develop a tourism destination recommendation chatbot based on content-based filtering integrated with the Telegram platform. The methods employed include text data preprocessing, vectorization using Term Frequency–Inverse Document Frequency (TF-IDF), and similarity measurement using cosine similarity. The chatbot is designed using a rule-based approach to receive user preference inputs in the form of keywords and generate relevant tourism destination recommendations in real time. The implementation and testing results indicate that the system is able to provide tourism recommendations that align with user preferences and respond effectively to various input variations. Therefore, the developed chatbot system can serve as a practical solution for delivering tourism information and recommendations in Takengon City and has the potential to be applied to other regions with similar characteristics.

Keywords: Chatbot, Recommendation System, Content-Based Filtering, TF-IDF, Cosine Similarity.