Enhancing Learning Management Systems with AI: Recommendations from Moodle Usage

Enhancing Learning Management Systems with AI: Recommendations from Moodle Usage Razika LOUNAS1 1LIMOSE Laboratory, Computer Science Department, Faculty of Sciences University of M’hamed Bougara of Boumerdes, Independency Avenue, 35000 Algeria, [email protected] Abstract Learning Management Systems (LMS) are defined as web-based platforms designed to facilitate the planning, delivery, management, and assessment of educational courses and training programs. These systems provide a structured virtual environment where learners, instructors, and administrators can interact through various tools. With the advent of artificial intelligence, several approaches have been explored to reshape and adapt LMS functionalities, enhancing their ability to meet the growing demand for AI-based tools in various pedagogical activities. Among existing LMS platforms, Moodle is one of the most widely used. It facilitates online education and offers a rich array of tools. However, feedback from computer science students highlights both its strengths and areas for improvement, particularly in terms of usability, engagement, and automation. This paper analyzes student feedback and examines how artificial intelligence (AI) can address common challenges in Moodle. Furthermore, it discusses potential AI-driven enhancements based on student insights and proposes recommendations for future research and implementation. Keywords: Learning Management systems, Moodle, Student’s perception, Artificial Intelligence. 1 Introduction The rapid advancement of information and communication technologies (ICTs) has significantly transformed various aspects of daily life, including education. Over the past decades, learning environments have evolved in response to major technological shifts, such as the rise of the internet, the introduction of Web 2.0 applications, and more recently, the emergence of artificial intelligence (AI)-driven tools [13,31]. These developments have reshaped how educational content is delivered, accessed, and personalized. In particular, Learning Management Systems (LMS) have become essential in modern education, enabling institutions to manage courses, facilitate communication, and support online learning. LMS platforms accommodate various teaching and learning methodologies, offering tools for content delivery, assessments, collaboration, and administrative management. However, as technology continues to advance, LMS platforms must adapt to evolving educational needs and user expectations. The COVID-19 pandemic accelerated the global reliance on LMS platforms, highlighting both their strengths and limitations. Institutions worldwide were compelled to transition rapidly to online learning, revealing challenges related to usability, student engagement, automation, and scalability [22]. Among the widely adopted LMS platforms, Moodle stands out due to its open-source nature, flexibility, and extensive adoption by universities and institutions worldwide, including in Algeria. Its features, such as collaborative tools, integration with external applications, and customizable learning environments, contribute to its success [11]. However, feedback from computer science students suggests areas for improvement, particularly in terms of usability, functionality, and interactivity. This paper explores the evolution of LMS platforms and examines how AI-driven enhancements could address current limitations in Moodle. By leveraging intelligent tutoring systems, automated grading, AI-powered chatbots, and adaptive learning algorithms, AI has the potential to enhance personalized learning, improve engagement, and optimize administrative tasks. The insights presented in this paper are based on reflections and feedback from Master’s level computer science students, who offer valuable perspectives on potential improvements at various levels, including functionality, usability, and advanced AI-driven features. This paper aims to: •Provide an overview of LMS evolution and highlight challenges in Moodle. •Analyze student feedback to identify key areas for improvement. 200 •Propose AI-driven enhancements that could improve interactivity, automation, and personalization. The rest of this paper is organized as follows: Section 2 presents an overview on LMS and AI integration. Section 3 presents the methodology used for gathering student insights. Section 4 outlines key findings and proposed AI-based recommendations. Finally, Section 5 concludes the paper. 2 Background 2.1 LMS Overview A Learning Management systems (LMS) is defined as virtual environment that aims to simulate faceto-face learning environments with the use of Information Technology applications, and customizable learning environments, contribute to its success [27]. The interactions among different users (student, teacher, administrative) happen through the system that provides synchronous or asynchronous communication tools. LMS provide a large plethora of functions allowing the creation of different strategies and learning modes and to engage learners. Figure 1: LMS functions Learning Management System (LMS) are designed to include several components that support online education course administration, and student engagement [29,19]. The main functions of an LMS are depicted in Figure 1. Course registration and administration module manages user roles, course enrollment, group organization, scheduling, and authentication. Content delivery enables both synchronous and asynchronous learning, supporting various formats such as videos, interactive materials, and allow students to engage flexibly with course content by offering possibility to connect with different devices. To monitor progress, LMS platforms integrate tracking and learning analytics, providing insights into student engagement, course completion rates, and attendance. Another essential component is collaboration and communication, which fosters interaction through chat systems, discussion forums, shared calendars, and resource-sharing tools, while also offering advanced collaboration features such as wikis and co-creation workspaces. Effective course material management ensures that educational resources are organized, and accessible, integrating with different types of repositories. Finally, the assessment and evaluation module facilitates automated quizzes, peer reviews, Exams, and competency-based assessments, allowing instructors to efficiently measure learning outcomes. Together, these components create a comprehensive digital learning environment, enabling institutions to deliver engaging, interactive, and structured online education. 2.2 Artificial Intelligence in LMS With the advent of artificial intelligence applications, learning management systems through their components have evolved to adapt to the new requirements. Several efforts have been made to improve the 201 LMS function with artificial intelligence applications and tools [9,7,1]. This section aims to present the current utilization of AI in Learning Management Systems by exploring the interaction of AI with every aspect of LMS and providing references supporting the integration and elucidating the benefits and challenges of such endeavor. Table 1 illustrates AI enhancements for every LMS components with supporting references. Table 1: AI Enhancements for LMS Components LMS Component AI Enhancements Registration and Administration AI-based automated student registration [18], intelligent course recommendations [25,21], and adaptive scheduling [5,15]. Content Delivery Personalized learning paths [33,16], adaptive content recommendations [8,30], and real-time AI tutoring [12,34]. Tracking and Analytics Predictive analytics for student performance [20,6], engagement tracking [14]. Collaboration Chatbots for student assistance, automated discussion moderation, and intelligent group formation [26,24]. Course Material Management Assisted content organization, tagging and summarization, and intelligent resource recommendations [35,23,4]. Assessment and Evaluation Automated essay scoring and plagiarism detection, [2,10]. The table 1illustrates the availability of research on the integration of AI tools and applications to enhance learning management systems (LMS) at different levels. It is worth noting that the integration of artificial intelligence in LMS has shifted significantly with the advent of generative AI. Indeed, tools like ChatGPT have revolutionized LMS functionalities with their unique capabilities in natural language understanding and content generation [28]. These advancements have enabled more interactive and adaptive learning experiences facilitating AI-based tutoring and assistance, assessment, and personalization. Among existing platforms, Moodle is a fundamental tool in modern education, particularly in computer science programs. It facilitates course management, content delivery, and student-teacher interaction. AI applications have been integrated into various aspects of LMS platforms through several initiatives [17]. However, student feedback continues to highlight usability concerns, a lack of real-time support, and difficulties in navigating and engaging with course materials. This indicates that the integration of AI tools remains an active research area. The aim of this study is to analyze feedback from computer science students on Moodle and explore how AI technologies can enhance its functionality. 3 Methodology This section outlines the research methodology used in this study. It begins by describing the research model, followed by details on the context, participants, and data collection. 3.1 Research Model This study is based on a qualitative research approach. Qualitative research focuses on understanding meanings, experiences, and concepts from the perspective of participants. Its objective is to gain insights into social phenomena, events, or complex issues. This type of research was adopted because it is best suited to capture the different aspects of users’ reactions to the use of Moodle platform enabling the evaluation of its strengths, weaknesses, and potential improvements [3]. To gather data, the study employs a questionnaire, which is one of the most commonly used tools in educational technology research. The questionnaire consists of open-ended questions, allowing assessment and qualitative insights. The collected responses are analyzed to identify trends, user satisfaction, and key areas where AI-driven enhancements could improve the platform. 202 3.2 Context and Participants The study was conducted with final-year Master’s students from the Computer Science Department of Boumerdes University. A total of 54 students participated in the survey. As young engineers and future professionals, their insights are particularly valuable in identifying technical and functional improvements for the Moodle platform. The questionnaire covered three main areas: •Advantages of Moodle: Students were asked to identify key benefits of using the platform. •Challenges and Limitations: Participants highlighted areas they think about as Moodle limitaions. •Suggestions for Improvement: As computer science students, participants provided some directions to enhance the platform. The collected data was analyzed qualitatively to identify recurring patterns and common themes. Additionally, percentage distributions were used to highlight the frequency of reported advantages and challenges. The results provide insights and a base for recommendations for improving Moodle’s usability and performance. 4 Results This section presents students’ feedback related to the questions about advantages, inconveniences, and possible improvements for Moodle. The last point serves as a basis to propose recommendations for improvements by including AI tools and applications. 4.1 Strengths of the platform The number of students responding to the question about Moodle advantages is twenty six (26 students). The following key points emerged about the platform strengths: flexibility and accessibility, collaboration, pedagogical support, security and data protection, and digital skills development. The data are reported on Table 2. The majority of students (88%) pointed out the advantage of the platform flexibility and accessibility. The platform is open-source platform, free and highly customizable. Moodle supports distance learning by eliminating spatial and temporal constraints. The platform benefits also from an active global community that provides extensive documentation and support. The platform is widely adopted by universities, high schools, and businesses. The student also highlighted the advantage of collaboration. Indeed, the platform enables extensive communication between students and teachers. with a rich range of features from simple messaging and forums to more advanced features such as wikis. Coordination is facilitated by planning tools such as shared agendas. Co-production, information sharing, and knowledge management are also features that enhance collaborative work within the learning process, fostering an interactive and engaging educational environment. Pedagogical Support is mentioned as an advantage of Moodle. Diverse resource formats and evaluation methods are available, enabling teachers to monitor student progress, provide feedback, track behaviors, and digitally assess assignments. The platform is widely used across various educational and organizational contexts, fostering a large community of users and shared resourcese. Its features help address challenges such as student absences by maintaining course records before, during, and after sessions. With a wide range of integrated tools, online assessment methods, and compatibility with institutional learning environments, Moodle enhances both teaching effectiveness and student engagement. Several students mentioned also security and data protection. The platform offers various mechanisms to protect user data and ensure safe usage. It includes access control features to prevent unauthorized access making Moodle a reliable choice for institutions that prioritize data protection in online learning environments. Finally, some students (15%) mentioned digital Skills development as an advantage of Moodle since from their point of view Moodle contributes to the development of students’ digital skills by providing an environment that encourages the use of technology in learning. The interaction with the platform allow students to enhance their ability to navigate digital tools, manage online resources, and engage in technology-assisted learning. 203 Table 2: Advantages of Moodle as reported by students Advantage % of Students mentioning it Flexibility and accessibility 88% Collaboration 50% Pedagogical support 65% Security and data protection 38% Digital skills development 15% 4.2 Weaknesses of the platform The number of students who responded to the question of the platform weaknesses is 28. It is a different group from the students who responded to the question of advantages. According to students feedback, the platform suffers from several drawbacks that are categorized into four categories as depicted by Table 3: Interface and Usability Issues, lack of personalization, socialization issues, and integration and compatibility problems. The issues with the interface and use were the most mentioned weakness. Students frequently expressed dissatisfaction with Moodle’s interface, describing it as unattractive, un-intuitive, and outdated. Many reported difficulties navigating the platform. There is a strong demand for a more modern and ergonomic design. Additionally, slow system performance and long loading times make access to learning materials difficult. Several students expressed the need for technical support and training to help users better navigate and utilize the platform’s features effectively. The second raised issue is related to personalization: Students highlighted Moodle’s limited customization options as a drawback. The platform does not sufficiently adapt to students’ specific needs, making it difficult to adapt the learning experience. Many users expressed a request for personalization, both in terms of content and page appearance, to create a more engaging and individualized environment. Students also raised the need for socialization: they highlighted the lack of features that enhance social interaction, particularly the need for better support for group work. They also pointed out the absence of more engaging activities inspired by social networks, such as the ability for students to publish content and collaborate on co-produced materials. Problems related to integration and compatibility are also reported by students. Students reported difficulties in integrating Moodle with external tools such as Google Drive, Slack, and Zoom, which are highly used in their learning activities. Issues with mobile compatibility are also mentioned , noting that the platform does not always function easily on smartphones and the lack of proper synchronization across devices makes it difficult to use. Table 3: Weaknesses of Moodle as reported by students Weakness % of students mentioning it Interface and usability issues 88% Lack of personalization 46% Socialization issues 23% Integration and compatibility problems 23% 4.3 Suggestions for Moodle improvements The objective of this section is first to present students’ suggestions according to the raised issues. These suggestions with the weaknesses that are pointed out by students serve a a basis to some recommendations about the use of AI to enhance the platform. 4.3.1 Suggesions from students The word cloud (see Figure 2) visually represents the most frequently mentioned suggestions from students regarding Moodle’s improvement. The larger words indicate the most common themes, highlighting key areas of concern and potential enhancements. From this visualization, it is evident that students prioritize aspects such as interface modernization, personalization, integration with other tools, and per204 Figure 2: Word cloud from students suggestions formance optimization. These insights reinforce the need for a more intuitive and interactive learning environment that aligns with user expectations. While the word cloud effectively illustrates the most recurring themes in students’ feedback, it is important to note that some valuable suggestions may not appear prominently due to lower mention frequency. For instance, proposals such as integrating artificial intelligence for personalized learning, providing instant feedback, or enhancing course recommendations were mentioned by a smaller number of students but still represent innovative directions for improvement. These insights, though less common, highlight valuable enhancements that could significantly impact Moodle’s users experience. 4.3.2 Recommendations for Improvements with Artificial Intelligence To address the issues raised by students about Moodle, AI can be leveraged in several ways: •Interface and usability issues: In response to this issue, the incorporation of artificial intelligence could be used to predict user behavior in order to anticipate and address potential barriers to use in UI design. This will not only improve the user experience, but also promote the development of UI design in a more user-friendly and intelligent direction. In addition, advanced concepts such as immersive environments in LMS can be explored [32]. Furthermore, virtual assistants to help navigating the platform could be developed to enhance its efficiency and usability. •Personalization: To enhance the personalization aspect in Moodle and provide a learning experience adapted for students, several artificial intelligence approaches may be explored. While the course are generally mandatory, recommendations may occur at the level of resources. In addition, the use of expert systems and intelligent tutors that adapt to user needs are also a perspective suitable to Moodle. Studies on AI in education show that intelligent tutoring systems and automated assessment tools improve student engagement and learning outcomes. These tools can analyze student performance and recommend personalized study materials, and adjust difficulty levels based on student progress. •Socialization: Several research directions and applications of AI are suitable to this concern. The use of community detection tools may be used to form group discussions about academic topics or homework for students. In addition, chatbots and discussion moderators can facilitate meaningful conversations, ensuring that discussions remain relevant and productive. Sentiment analysis tools may also be integrated to detect and address students’ concerns in forums, promoting a more engaging and supportive learning environment. •Integration and Compatibility Problems: AI can help with compatibility issues by automating content adaptation for different devices and browsers. Additionally, artificial intelligence can facilitate communication between Moodle and other platforms, ensuring smooth data exchange and reducing technical disruptions for both students and educators. 205 5 Conclusion Learning Management Systems (LMS) have revolutionized digital education by providing a structured and interactive environment for learning. This study explored LMS platforms, particularly Moodle through students’ perception. The platform offers numerous advantages such as accessibility, collaboration, pedagogical support, security, and flexibility. However, student feedback reveals critical areas for improvement, particularly user interface design, personalization, social interaction, and integration with external tools. The integration of Artificial Intelligence (AI) into LMS platforms presents an opportunity to address these challenges and enhance the overall learning experience. AI applications and features such as adaptive learning, intelligent tutoring systems, automated content recommendations, and predictive analytics can significantly improve the students’ experience in LMS. Furthermore, the emergence of Large Language Model (LLM) chatbots like ChatGPT can reshape student interactions within learning environments. This paper provides some recommendations for the use of AI in Moodle. Future directions of this research will addresss some limitations such as the inclusion of teachers perception, complete with a quantitative research, and the effective development of improvements based on AI. References [1] Nouf Aldahwan and Norah Alsaeed. Use of artificial intelligent in learning management system (lms): a systematic literature review. International Journal of Computer Applications, 175(13):16– 26, 2020. [2] Abdulaziz Salamah Aljaloud, Diaa Mohammed Uliyan, Adel Alkhalil, Magdy Abd Elrhman, Azizah Fhad Mohammed Alogali, Yaser Mohammed Altameemi, Mohammed Altamimi, and Paul Kwan. A deep learning model to predict student learning outcomes in lms using cnn and lstm. IEEE Access, 10:85255–85265, 2022. [3] Ann Blandford, Dominic Furniss, and Stephann Makri. Qualitative HCI research: Going behind the scenes. Morgan & Claypool Publishers, 2016. [4] Hui Chen, Chuantao Yin, Rumei Li, Wenge Rong, Zhang Xiong, and Bertrand David. Enhanced learning resource recommendation based on online learning style model. Tsinghua science and technology, 25(3):348–356, 2019. [5] Prithviraj Dasgupta and Deepak Khazanchi. Adaptive decision support for academic course scheduling using intelligent software agents. International Journal of Technology in Teaching and Learning, 1(2):63, 2005. [6] Ashish Dutt and Maizatul Akmar Ismail. Can we predict student learning performance from lms data? a classification approach. In Proceedings of the 3rd International Conference on Current Issues in Education (ICCIE 2018), pages 24–29. Atlantis Press, 2019. [7] Mohd Elmagzoub Eltahir and Frdose Mohd Elmagzoub Babiker. The influence of artificial intelligence tools on student performance in e-learning environments: Case study. Electronic Journal of e-Learning, 22(9):91–110, 2024. [8] Digna S Evale. Learning management system with prediction model and course-content recommendation module. Journal of Information Technology Education: Research, 16(1), 2017. [9] Mehmet Fırat. Integrating ai applications into learning management systems to enhance e-learning. Instructional Technology and Lifelong Learning, 4(1):1–14, 2023. [10] A Jauhar Fuad, Amar Kukuh Wicaksono, M Auzai Aqib, M Arif Khoiruddin, Abbas Sofwan Matla’Il Fajar, and Khoirul Mustamir. Ai hybrid based plagiarism detection system creation. In 2024 4th International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), pages 1495–1500. IEEE, 2024. [11] Sithara HPW Gamage, Jennifer R Ayres, and Monica B Behrend. A systematic review on trends in using moodle for teaching and learning. International journal of STEM education, 9(1):9, 2022. 206 [12] Cecilia Estela Giuffra Palomino, Ricardo Azambuja Silveira, and Marina Keiko Nakayama. An intelligent lms model based on intelligent tutoring systems. In Intelligent Tutoring Systems: 12th International Conference, ITS 2014, Honolulu, HI, USA, June 5-9, 2014. Proceedings 12, pages 567–574. Springer, 2014. [13] Abid Haleem, Mohd Javaid, Mohd Asim Qadri, and Rajiv Suman. Understanding the role of digital technologies in education: A review. Sustainable Operations and Computers, 3:275–285, 2022. [14] Curtis R Henrie, Robert Bodily, Ross Larsen, and Charles R Graham. Exploring the potential of lms log data as a proxy measure of student engagement. Journal of Computing in Higher Education, 30:344–362, 2018. [15] Bui Thi Thanh Huong, Tran Van Cong, Ton Quang Cuong, and Nguyen Duc Nguyen. Smart schedule: Training management approach in the digital education era. In Digital Education for the 21st Century, pages 283–305. Apple Academic Press, 2021. [16] Delara Jafari and Zahra Shaterzadeh-Yazdi. Transforming education with ai: The development of a personalized learning algorithm for individual learning styles. Journal of Algorithms and Computation, 56(2):135–150, 2024. [17] Devkan Kaleci. Integration and application of artificial intelligence tools in the moodle platform: A theoretical exploration. Journal of Educational Technology and Online Learning, 8(1):100–111, 2025. [18] Vishesh Kalvakurthi, Aparna S Varde, and John Jenq. Hey dona! can you help me with student course registration? arXiv preprint arXiv:2303.13548, 2023. [19] Nurul Nadirah Mohd Kasim and Fariza Khalid. Choosing the right learning management system (lms) for the higher education institution context: A systematic review. International Journal of Emerging Technologies in Learning, 11(6), 2016. [20] Majid Khan, Saba Naz, Yashir Khan, Muneeb Zafar, Maqbool Khan, and Giovanni Pau. Utilizing machine learning models to predict student performance from lms activity logs. IEEE Access, 11:86953–86962, 2023. [21] Hassan Khosravi, Kirsty Kitto, and Joseph Jay Williams. Ripple: A crowdsourced adaptive platform for recommendation of learning activities. arXiv preprint arXiv:1910.05522, 2019. [22] Christopher M Lee. Impact of learning management systems (lms) toward students during the covid-19 pandemic. Available at SSRN 4854926, 2023. [23] Debabrata Mahapatra, Ragunathan Mariappan, Vaibhav Rajan, Kuldeep Yadav, and Sudeshna Roy. Videoken: Automatic video summarization and course curation to support learning. In Companion Proceedings of the The Web Conference 2018, pages 239–242, 2018. [24] Elizaphan M Maina, Robert O Oboko, and Peter W Waiganjo. Using machine learning techniques to support group formation in an online collaborative learning environment. International Journal of Intelligent Systems & Applications, 9(3):26–33, 2017. [25] Dina Fitria Murad, Yaya Heryadi, Bambang Dwi Wijanarko, Sani Muhamad Isa, and Widodo Budiharto. Recommendation system for smart lms using machine learning: a literature review. In 2018 international conference on computing, engineering, and design (ICCED), pages 113–118. IEEE, 2018. [26] Giacomo Nalli, Daniela Amendola, and Serengul Smith. Artificial intelligence to improve learning outcomes through online collaborative activities. In European Conference on e-Learning, pages 475–479. Academic Conferences International Limited, 2022. [27] Paulo Cristiano de Oliveira, Cristiano Jose Castro de Almeida Cunha, and Marina Keiko Nakayama. Learning management systems (lms) and e-learning management: an integrative review and research agenda. JISTEM-Journal of Information Systems and Technology Management, 13(2):157–180, 2016. 207 [28] Sameer Qazi, Muhammad Bilal Kadri, Muhammad Naveed, Bilal A Khawaja, Sohaib Zia Khan, Muhammad Mansoor Alam, and Mazliham Mohd Su’ud. Ai-driven learning management systems: Modern developments, challenges and future trends during the age of chatgpt. Computers, Materials & Continua, 80(2), 2024. [29] Rabiman Rabiman, Muhammad Nurtanto, and Nur Kholifah. Design and development e-learning system by learning management system (lms) in vocational education. Online Submission, 9(1):1059–1063, 2020. [30] Nisha S Raj and VG Renumol. A rule-based approach for adaptive content recommendation in a personalized learning environment: An experimental analysis. In 2019 IEEE tenth international conference on technology for education (T4E), pages 138–141. IEEE, 2019. [31] Ido Roll and Ruth Wylie. Evolution and revolution in artificial intelligence in education. International journal of artificial intelligence in education, 26:582–599, 2016. [32] Serhiy O Semerikov, Tetiana A Vakaliuk, Iryna S Mintii, Vita A Hamaniuk, Olha V Bondarenko, Pavlo P Nechypurenko, Svitlana V Shokaliuk, and Natalia V Moiseienko. Immersive cloud-based educational environment of the university: Design principles. CEUR Workshop Proceedings, 2024. [33] MJKMS Somasundaram, KA Mohamed Junaid, and Srinivasan Mangadu. Artificial intelligence (ai) enabled intelligent quality management system (iqms) for personalized learning path. Procedia Computer Science, 172:438–442, 2020. [34] Marwa Soudi, Esraa Ali, Maha Bali, and Nihal Mabrouk. Generative ai-based tutoring system for upper egypt community schools. In Proceedings of the 2023 Conference on Human Centered Artificial Intelligence: Education and Practice, pages 16–21, 2023. [35] Christopher CY Yang, Irene YL Chen, G¨okhan Ak¸capınar, Brendan Flanagan, and Hiroaki Ogata. Using a summarized lecture material recommendation system to enhance students’ preclass preparation in a flipped classroom. Educational Technology & Society, 24(2):1–13, 2021. 208