Pengembangan Aplikasi Chatbot Telegram Menggunakan Framework Rasa untuk Pelayanan Administrasi di Perguruan Tinggi Universitas Stikubank

Abstract

The administrative services in universities are currently still conventional, resulting in many difficulties due to the mismatched time. For this research, a Telegram chatbot application will be developed to provide various answers to administrative inquiries in universities automatically. The chatbot application will be developed using the Rasa Open Source framework. This research collects data from several frequently asked questions by students and prospective students to the Biro Administrasi Akademik dan Kemahasiswaan (BAAK) as the initial data for the chatbot application. From this data, it will be transformed into Natural Language Understanding (NLU) and dialogue data. The number of NLU sentence examples is 213, and there are 27 dialogue examples. As a result, the chatbot application can understand user inquiries well, but it experiences some errors in generating dialogue responses.