Development and Analysis of an Academic Assistant Chatbot for Dalarna University : Improving Information Accessibility through a GPT-Based Chatbot
Year: 2025
Type: dissertation
Abstract: This thesis explores the usability and effectiveness of a GPT-based chatbot developed to help students at Dalarna University find academic information. The study was done under the interdisciplinary Informatics and Microdata Analysis framework, fusing system development with an empirical evaluation of user behavior. First, a mixed-methods approach was undertaken in which six participants took part in a controlled experiment relating them into two groups: one for the university’s website and another for the chatbot. Each group performed identical information-seeking tasks followed by semi-structured interviews. User qualitative feedback was analyzed thematically to triangulate quantitative data from chatbot logs and task completion times. Findings show that the chatbot ran faster in task completion and was more user-friendly than the website. Usability, trust, and information accessibility emerged as key themes from the interviews. Results were interpreted through the Technology Acceptance Model (TAM). It showed elevated levels of perceived usefulness and ease of use leading to user trust and intention to reuse the chatbot. In addition, usage logs revealed common query patterns and task types, offering insights into how the chatbot’s design and performance could be further refined. This study adds to the emerging research on AI-driven student services and how conversational interfaces can improve information retrieval in higher education such as Dalarna University. Ethical considerations, limitations of system design, and future research directions are also discussed.
Authors: Gumus, Sahin, Jouma, Roni, Sulja, Mergim
Institution: Dalarna University
Language: English
Topic: AI in Service Interactions
Subfield: Marketing
Domain: Social Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W7055908146
