Publicação
Empirical Analysis of an AI-Powered Chatbot for Enhancing University Information Retrieval
| Resumo: | This thesis examines the implementation and evaluation of an AI-powered chatbot for improving information retrieval processes at Kozminski University. Leveraging the DeLone and McLean Model of Information Systems Success, the study assesses the chatbot’s impact on user efficiency, information quality, and satisfaction, as well as its implications for the university’s existing knowledge management practices. The empirical study involves comparative testing between the AI chatbot and Kozminski Knowledge Base, the traditional repository of institutional information. The outcomes indicate that the chatbot significantly reduces information retrieval time and improves accuracy while enhancing user satisfaction. This research not only contributes a viable AI solution for educational institutions but also provides empirical evidence of its effectiveness, potentially advancing the integration of AI applications in higher education. The research contributes theoretically by extending the application of the DeLone and McLean Model to chatbot technology and practically by providing insights into implementing AI chatbots in higher education contexts. Despite its promising findings, the study acknowledges limitations, including its focus on a single institution and a specific chatbot implementation. Future research directions are proposed to explore broader applicability, advanced AI features, and long-term impacts on knowledge management. This thesis underscores the transformative potential of AI chatbots as a key tool for improving information retrieval in academic settings. |
|---|---|
| Autores principais: | Spasibukhov, Artem |
| Assunto: | Artificial Intelligence Chatbots Technologies Large Language Models Natural Language Processing Informational Systems SDG 4 - Quality education SDG 9 - Industry, innovation and infrastructure |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | This thesis examines the implementation and evaluation of an AI-powered chatbot for improving information retrieval processes at Kozminski University. Leveraging the DeLone and McLean Model of Information Systems Success, the study assesses the chatbot’s impact on user efficiency, information quality, and satisfaction, as well as its implications for the university’s existing knowledge management practices. The empirical study involves comparative testing between the AI chatbot and Kozminski Knowledge Base, the traditional repository of institutional information. The outcomes indicate that the chatbot significantly reduces information retrieval time and improves accuracy while enhancing user satisfaction. This research not only contributes a viable AI solution for educational institutions but also provides empirical evidence of its effectiveness, potentially advancing the integration of AI applications in higher education. The research contributes theoretically by extending the application of the DeLone and McLean Model to chatbot technology and practically by providing insights into implementing AI chatbots in higher education contexts. Despite its promising findings, the study acknowledges limitations, including its focus on a single institution and a specific chatbot implementation. Future research directions are proposed to explore broader applicability, advanced AI features, and long-term impacts on knowledge management. This thesis underscores the transformative potential of AI chatbots as a key tool for improving information retrieval in academic settings. |
|---|