New Perspectives in Science Education

Edition 14

Accepted Abstracts

Advisely: AI-Powered Academic Advising Using Large Language Models (LLMs)

Sherif Abdelhamid, Assistant Professor, Virginia Military Institute (United States)

James Bangura, Virginia Military Institute (United States)

Shahryar Shah, Virginia Military Institute (United States)

Abstract

Academic advising is a crucial component of student success in higher education, providing guidance on course selection, program requirements, navigating institutional policies, and much more. It significantly influences students' academic performance, retention, and educational experience. However, current advising practices often face challenges such as limited accessibility, inconsistent information, miscommunication, and high administrative workloads. To address these challenges, this paper introduces Advisely, a web-based platform that employs GPT-4, a large language model, to facilitate academic advising. The system integrates the AI-powered chatbot with a comprehensive knowledge base covering academic policies, regulations, and institutional requirements. Advisely is designed to support students, academic advisors, and faculty by providing reliable, context-aware guidance on various topics, including course selection, program requirements, and policy interpretation. The platform’s architecture features a decoupled front-end interface and back-end knowledge base, allowing institutions to update policies and rules without disrupting the user experience. This separation ensures scalability and flexibility, enabling each school to integrate its resources, regulations, and program-specific information. The paper discusses different use cases that illustrate Advisely’s practical application, such as guiding students through course enrollment, clarifying graduation requirements, and aiding advisors in providing consistent advice. An initial evaluation assesses the system's performance regarding response accuracy and consistency. Findings suggest that Advisely significantly enhances the academic advising process, reducing administrative workload and improving access to information. Feedback from early users informs future development, aiming to expand functionality and refine the chatbot's capabilities for broader deployment.

 

Keywords

Academic advising, Student success, Large Language Model, GPT-4, Artificial Intelligence

 

REFERENCES

[1] Bilquise, G. and Shaalan, K. (2022). Ai-based academic advising framework: a knowledge management perspective. International Journal of Advanced Computer Science and Applications, 13(8).

[2] Frezghi, T. (2019). Undergraduate students’ perceptions on academic advising in Eritrean higher education: a case study of Eritrea Institute of Technology. International Journal of Research Studies in Education, 8(3).

[3] Hoai Nam, N. T. and Giang, N. T. H. (2023). Design of knowledge flow according to the approach of self-regulation learning for teaching maths on chatbot. International Journal of Current Science Research and Review, 06(12).

[4] Almogren, A. S., Al-Rahmi, W. M., & Dahri, N. A. (2024). Exploring factors influencing the acceptance of chatgpt in higher education: a smart education perspective. Heliyon, 10(11), e31887.

 

Back to the list

REGISTER NOW

Reserved area


Media Partners:

Click BrownWalker Press logo for the International Academic and Industry Conference Event Calendar announcing scientific, academic and industry gatherings, online events, call for papers and journal articles
Pixel - Via Luigi Lanzi 12 - 50134 Firenze (FI) - VAT IT 05118710481
    Copyright © 2024 - All rights reserved

Privacy Policy

Webmaster: Pinzani.it