Development of an Intelligent Student Advisory Chat System

Abstract

Development of a Student Advisory (STAD) system, which is able to provide responses to students on questions that they would usually ask their academic advisers, is the research presented in this paper. A knowledge base was built into the system using Dialogflow - Google's Natural Language Understanding module, which allowed the system to be trained as an agent using phrases or sentences that students are likely to use when communicating with advisors for each context or category of conversation referred to as intent. Information used to build the knowledge base and train the system was gathered from online and offline sources, including the student handbook, students, advisors, and a questionnaire. The information was organized and categorized to determine different intents and possible parameters. Conversation design was carried out to simplify the process and make the system somewhat interactive and conversational using the gathered information. The system was implemented using the Python Django framework and was evaluated using alpha-beta testing. A student advisory system was developed in the form of a chatbot,which is easily accessible, accepting phrases or sentences. It provides most of the necessary information students need to have successful academic sessions on the campus, as though they were communicating with an active advisor.