View in EDS

Integrating chatbots with learning management systems for personalized learning: a comprehensive review and framework proposal—the CLIF.

Saved in:
Bibliographic Details
Title: Integrating chatbots with learning management systems for personalized learning: a comprehensive review and framework proposal—the CLIF.
Authors: Wong, Adam Ka Lok1 (AUTHOR) adam.wong@cpce-polyu.edu.hk, Chan, Lai Lam1 (AUTHOR) lailam.chan@speed-polyu.edu.hk
Source: Discover Education. 11/28/2025, Vol. 4 Issue 1, p1-26. 26p.
Subject Terms: *Learning management system, *Educational technology, *Individualized instruction, *Student engagement, *Learning, *Gamification, Chatbots, Software frameworks
Abstract: Chatbots are versatile tools with significant potential to enhance education, particularly by enabling personalized learning. Personalized learning in higher education is most effectively achieved using data from Learning Management Systems (LMS). However, many educators remain unaware of the different approaches LMS data can facilitate for personalization, as well as the advantages and limitations of these approaches. This study critically reviews current research on chatbot LMS integration, emphasizing their ability to address educational challenges like real-time student engagement, automated assessment, and gamification strategies. Furthermore, it also identifies gaps in the existing body of research, particularly the limited focus on personalization in chatbot applications. To address these gaps, the study introduces the Chatbot LMS Integration Framework (CLIF), which categorizes chatbots based on their technical integration and their use of LMS data for personalization. The framework serves as a guide for future research and educational practices, aiming to strike a balance between the skills and time required to build chatbots and their functionality and adaptability. The research adhered to the PRISMA procedure, starting with 1,431 articles and narrowing down to 18 for a detailed critical review. The findings underscore the need for more comprehensive empirical studies examining educators' and students' perceptions, as well as the effects of chatbots on academic performance. The CLIF framework is structured with three primary levels and two sub-levels within each, providing a detailed categorization. Of the 18 reviewed articles, only 13 included implementation results, which were used to plot the CLIF framework. This analysis highlights the framework's value in illustrating the benefits of personalized learning in comparison to the efforts and expertise required to develop educational chatbots that maximize student outcomes. [ABSTRACT FROM AUTHOR]
Copyright of Discover Education is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Education Research Complete
Description
Abstract:Chatbots are versatile tools with significant potential to enhance education, particularly by enabling personalized learning. Personalized learning in higher education is most effectively achieved using data from Learning Management Systems (LMS). However, many educators remain unaware of the different approaches LMS data can facilitate for personalization, as well as the advantages and limitations of these approaches. This study critically reviews current research on chatbot LMS integration, emphasizing their ability to address educational challenges like real-time student engagement, automated assessment, and gamification strategies. Furthermore, it also identifies gaps in the existing body of research, particularly the limited focus on personalization in chatbot applications. To address these gaps, the study introduces the Chatbot LMS Integration Framework (CLIF), which categorizes chatbots based on their technical integration and their use of LMS data for personalization. The framework serves as a guide for future research and educational practices, aiming to strike a balance between the skills and time required to build chatbots and their functionality and adaptability. The research adhered to the PRISMA procedure, starting with 1,431 articles and narrowing down to 18 for a detailed critical review. The findings underscore the need for more comprehensive empirical studies examining educators' and students' perceptions, as well as the effects of chatbots on academic performance. The CLIF framework is structured with three primary levels and two sub-levels within each, providing a detailed categorization. Of the 18 reviewed articles, only 13 included implementation results, which were used to plot the CLIF framework. This analysis highlights the framework's value in illustrating the benefits of personalized learning in comparison to the efforts and expertise required to develop educational chatbots that maximize student outcomes. [ABSTRACT FROM AUTHOR]
ISSN:27315525
DOI:10.1007/s44217-025-00958-w