The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Abstract


This study aims to analyze the effectiveness of AI Chatbot usage in academic information retrieval among students at the State Islamic University of North Sumatra. The research is motivated by the increasing adoption of artificial intelligence (AI) technology among Generation Z, particularly in the context of higher education. A quantitative descriptive approach was employed using a survey method, involving 404 respondents who completed a Likert-scale-based questionnaire. The results indicate that AI Chatbots are considered very effective, with the highest mean score of 4.2 in the response speed aspect. However, the accuracy and relevance of the information were rated as only moderately effective, with mean scores of 3.8 and 3.7, respectively. The chatbot is most frequently used for lecture-related needs (89.6%) and academic advising (73%), while its use for reference searches (46.3%) and administrative information (28.7%) remains limited. The primary challenge reported by students was difficulty in constructing appropriate prompts, with 88.1% experiencing such issues. The reliability test produced a Cronbach’s Alpha value of 0.827, indicating that the instrument used was reliable. These findings suggest that AI Chatbots hold potential to enhance academic information retrieval efficiency, although improvements are needed in contextual understanding and user interaction capabilities.


Keywords


AI Chatbot; Effectiveness; Academic Information; College Student