Abstract
The integration of chatbots into learning management systems (LMSs) has the potential to significantly enhance the user experience (UX) in the context of higher education. However, the lack of evidence-based guidelines for the design of such chatbots has diminished this potential. This study proposes a set of guiding principles to improve the design of LMS chatbots. A design science research approach was adopted to formulate the chatbot design principles, drawing on insights from 12 LMS users (students, instructors and administrators) at diverse higher education institutions, gathered during a design thinking workshop and refined through expert evaluation. This study offers a framework for developing LMS chatbots that prioritise UX, ensuring that LMS platforms remain an asset in Higher Education Institutions (HEIs). The principles address various aspects, including technical mechanisms, language usage, user experience and feedback mechanisms. Practically, it offers actionable principles to enhance responsiveness, accessibility, personalisation and trust. Future research should focus on the empirical evaluation of these principles in real-world implementations and their applicability to Artificial Intelligence (AI)-enabled chatbots to validate their effectiveness and broader impact on UX for users.
Contribution: This study proposes a structured, empirically grounded set of design principles for LMS-integrated chatbots. It addresses user dissatisfaction and underutilisation in LMS platforms by offering evidence-based guidance to enhance UX. It builds on and provides a framework for improving chatbot-user interactions. Practically, it offers actionable principles to enhance responsiveness, accessibility, personalisation and trust. This study thus supports digital transformation in higher education by promoting more engaging, inclusive and student-centred technology-enhanced learning environments.
Keywords: chatbots; design principles; design thinking workshop; higher education institutions; learning management systems; user experience.
Introduction
Higher Education Institutions (HEIs) worldwide rely on learning management systems (LMSs) to deliver course content, assess student learning and maintain effective communication. This transforms the educational landscape by providing a platform for managing academic content and facilitating interaction between students and educators (Turnbull, Chugh & Luck 2023). Despite their widespread adoption, LMS platforms are underutilised (Simon et al. 2024) and rarely provide an optimal user experience (UX) to LMS users (Yawisah et al. 2022). Existing user support mechanisms characteristic of these systems are frequently inadequate, leading to user dissatisfaction (Chen 2019) and, in some cases, prompting institutions to consider alternative solutions.
A potentially effective approach to addressing these UX challenges involves the integration of chatbots into LMS platforms. Chatbots are computer programs designed to replicate human conversation, and are used over the internet (Slater 2022). Walraven (2024) is of the opinion that chatbots should be fully integrated into the LMS platform to leverage existing resources such as course materials, assignments and user data. This integration ensures accessibility and relevance, as students can interact with the chatbot within a familiar platform. However, the successful implementation of LMS-integrated chatbots is hindered by the absence of well-defined design principles or guidelines specific to the LMS context. Existing chatbots often function as generic frequently asked question (FAQ) assistants or virtual lecturers, lacking the empirical foundation and integration necessary to significantly improve the UX of users (Mendoza et al. 2022). This leaves a significant gap in our understanding of how to design effective, user-centred LMS chatbots.
This study bridges this gap by developing a set of empirically grounded design principles for LMS chatbot design. Employing a Design Science Research (DSR) methodology, this study used a design thinking workshop to gather diverse perspectives from 12 active LMS users, including students, instructors and LMS administrators from various higher education institutions. Their contributions provided practical insights into user needs and experiences. Following this, the tentative set of design principles was evaluated by four LMS experts, comprising a project manager in university e-learning, two senior learning designers (one at a university and one at a private e-learning company), and the head of e-learning in an education innovation unit, who provided professional expertise to refine and validate the principles for broader applicability and effectiveness.
The research contributes not only to practice through the development of actionable design principles but also to theory by offering insights into how chatbot integration can enhance UX. As a result, this promotes greater adoption and utilisation of LMS platforms.
Literature review
Learning management system platforms have become integral to HEIs by providing a structured and efficient way to manage educational resources, facilitate learning and enhance access to education. They also enable institutions to monitor, assess and improve learning standards (Sesay & Sesay 2024). Learning management system platforms such as Blackboard, Moodle, Canvas and Brightspace serve as centralised repositories for course content, enabling seamless distribution and access. An LMS is a server-hosted software application that manages user, course and content information, providing a flexible platform for teaching and learning that overcomes the limitations of time and place (Simon et al. 2024). The significance of LMS platforms in HEIs lies in their ability to enhance the learning experience and administrative efficiency. Saleh et al. (2022) and Macayaon and Palomares (2023) emphasise LMSs’ role in fostering student motivation and, consequently, academic achievement. Learning management systems facilitate self-regulated learning (SRL), personalised content delivery and efficient administration through user-friendly web platforms. This makes them essential for modern educational practices (Al-Handhali, Al-Rasbi & Sherimon 2020; Walraven 2024).
Challenges and limitations of current learning management systems
Despite their widespread adoption and advantages, LMS platforms present various challenges, particularly related to UX. One primary issue is the rigidity of LMS platforms as they offer limited flexibility, which is needed for dynamic teaching and learning approaches. Chen (2019) criticises LMS platforms for being overly administrative and not sufficiently fostering student-centred, interactive learning experiences. Another significant challenge is the steep learning curve associated with LMS platforms. This necessitates effective and continuous training for users to be able to use these systems optimally (Allam et al. 2024; Almusharraf 2024). Inadequate maintenance and technical support can lead to substantial expenses and can potentially negatively impact user satisfaction and engagement (Lamo, Perales & De-la-Fuente 2022). Moreover, many LMS platforms offer limited support for mobile devices, which restricts accessibility and usability in an increasingly mobile-dependent world. Improving mobile-friendly interfaces is thus essential to supporting the growing use of smartphones and tablets for educational purposes (Az-Zahra, Nurhayati & Herlambang 2023).
User experience in educational technology
The integration of UX principles into educational technology is important for creating engaging and effective LMSs (Maslov, Nikou & Hansen 2021). As the field of UX design continues to evolve, it encompasses a broad range of disciplines and methodologies aimed at enhancing the overall interaction between users and digital products. In the context of LMSs, understanding and implementing good UX practices can significantly impact user satisfaction and educational outcomes.
To ensure the cohesive integration of LMS and UX elements and considerations, it is essential to recognise that the effectiveness of LMS platforms is intrinsically linked to their usability and user experience. While LMS platforms provide the infrastructure for educational content and administrative functions, the success of these systems hinges on their ability to offer an intuitive, user-friendly experience that meets the diverse needs of users.
Factors affecting user experience in learning management system
User satisfaction and engagement in LMS environments are influenced by several interconnected factors that collectively determine overall UX. Good UX in LMS is characterised by an intuitive interface that meets a user’s psychological need for autonomy, competence and relatedness, as well as by facilitating efficient interactions (Hassenzahl 2008; International Organization for Standardization [ISO] 2010). In this context, a well-designed LMS creates a user-friendly, enjoyable learning environment that directly supports educational goals. Key elements that enhance UX include:
- Accessibility and aesthetics: LMS platforms must be accessible to a broad audience, including users with disabilities, and should be visually appealing. A design that prioritises accessibility and attractive, consistent aesthetics can significantly enhance engagement and satisfaction (Cozlov & Zadorojnii 2022; Fleming 2023; Stoesz & Niknam 2022). Conversely, poor visual design and accessibility issues can detract from the user experience.
- Ease of use and functionality: A positive UX is further supported by platforms that are easy to navigate and enable the user to perform tasks efficiently. Simplified interfaces that minimise complexity while offering robust functionality are critical to improving user interaction (Demir, Bruce-Kotey & Alenezi 2022; Wenzel & Moreno 2022).
- Personalisation: Customisation features that allow LMS platforms to adapt to individual user preferences enhance the overall experience by ensuring that the system remains relevant to each user’s needs (Heng et al. 2022; Lima, Brito & Caldeira 2019).
Alternatively, factors such as excessive complexity, lack of accessibility and system instability can frustrate users and impair the learning experience (Liu et al. 2022; Ramesh, Vermette & Chilana 2021; Vandeyar 2020). Recent research suggests that enhancing attractiveness, efficiency and dependability can alleviate these challenges (Ibrahim & Aziz 2022).
Overall, addressing these UX challenges in LMS platforms calls for the incorporation of user-centred design principles that focus on making systems more accessible, interactive and responsive through effective feedback mechanisms (Almusharraf 2024; Walraven 2024).
Chatbots in education
Educational chatbots have become essential tools for enhancing user support and engagement in learning environments (Rane 2023). Their ability to provide immediate, personalised assistance fosters interactive learning, making them increasingly valuable in LMSs (Walraven 2024). Chatbots serve various functions, from acting as digital tutors (Hobert & Berens 2023) and supplementing instructors (Chen et al. 2023), to supporting SRL (Ifelebuegu, Kulume & Cherukut 2023). Frequently asked question bots also help to address common queries efficiently.
Studies have highlighted chatbots’ effectiveness in student engagement, personalised learning and instructional support. A systematic review by Kuhail et al. (2023) has found that chatbots improve learning outcomes and student satisfaction through interactive and flexible learning methods. Additionally, they enhance motivation and curiosity by providing timely assistance (Jei, Al-Rahili & Al-Farani 2024). Their 24/7 availability ensures continuous support, particularly benefiting remote students (Al-Sharhan et al. 2020; Rocio & Wesley 2020).
Despite their potential, limitations such as limited student involvement in chatbot design can impact their effectiveness (Kuhail et al. 2023). However, their role in transforming education through personalised and interactive learning remains substantial.
Existing chatbot design principles
Properly formulated design principles are fundamental in ensuring the creation of effective, user-friendly chatbots. These principles capture and generalise the knowledge gained from specific design instances, aiding in the design of artefacts that meet user needs and achieve desired objectives. Existing research on chatbot design principles has identified several key factors that contribute to effective and user-friendly chatbot interactions. These principles focus on enhancing transparency, engagement, adaptability, usability and ethical considerations to improve user experience and trust. The application contexts include virtual teams, enterprises and educational settings. A summary of existing chatbot design principles is provided in Table 1.
| TABLE 1: Existing chatbot design principles. |
In addition to the general chatbot design principles outlined in Table 1, Jung, Lee and Park (2020) examined design principles for educational chatbots by analysing human–chatbot interactions. Their study identifies the key roles that chatbots play in education and presents specific design principles tailored to each of these roles. These include tutor chatbots, evaluator chatbots, responder chatbots, moderator chatbots and peer-learner chatbots. Beyond these role-specific principles, their study also emphasises broader design principles from a UX perspective. Educational chatbots should maintain consistency in platform components to ensure a seamless UX. It is advised that they should further incorporate feedback mechanisms to minimise user waiting time and to enhance responsiveness. A natural conversational flow, including the use of appropriate humour, can make interactions more engaging and user-friendly. Additionally, chatbots should provide clear user guidance and feature an intuitive interface to enhance accessibility and ease of use. By adhering to these principles, educational chatbots can be designed to optimise learning experiences and improve overall user satisfaction.
Challenges in designing learning management system-integrated chatbots
Integrating chatbots into LMSs presents distinct challenges that go beyond those encountered in general educational applications. The key challenges include:
- Contextual adaptability: Chatbots must be flexible to accommodate diverse LMS environments, course structures and student demographics (Chaskopoulos et al. 2022).
- Technical integration: Compatibility with various LMS platforms, data security and maintaining system quality are critical concerns (Asenahabi, Peters & Nambiro 2022; Saroia & Gao 2019).
- User interaction and engagement: Chatbots should facilitate meaningful, interactive learning experiences rather than just answering questions (Kuhail et al. 2023).
- Usability for instructors: User-friendly interfaces are essential to enable instructors to configure and update chatbot functionalities efficiently (Ramandanis & Xinogalos 2023).
- Scalability and consistency: Managing large user volumes while maintaining response quality and system performance is a major technical challenge (Rane 2023).
While chatbot design principles provide a structured framework, LMS integration requires overcoming these distinct challenges to ensure effectiveness.
User experience honeycomb framework
The UX Honeycomb Framework (Morville 2004) served as the conceptual framework for this study, providing a comprehensive structure to explore and evaluate user experience beyond basic usability by encompassing multiple interconnected facets that shape the overall interaction. This model functions as a qualitative tool to assess how effectively a product or service meets user needs, ensuring a holistic and satisfying experience. By emphasising the integration and balance of various UX elements, the Honeycomb Model helps identify overlooked aspects in the early design stages, making it particularly useful for refining chatbot design principles within LMS platforms.
Additionally, the literature suggests that mapping out tentative design principles in the UX honeycomb aids in systematically addressing critical UX factors (Kim 2020). The model also acts as a checklist for designers, helping them to prioritise key objectives that align with user expectations (Desmet & Hekkert 2007; Kim 2020). Furthermore, by enabling comparisons across different cases, the Honeycomb Model facilitates the development of practical guidelines that enhance user satisfaction and engagement (Lee & Kim 2017). Given these advantages, this study adopts Morville’s UX Honeycomb Model (see Figure 1) to ensure the use of a holistic approach to designing chatbots for educational environments.
The Honeycomb Model includes seven interconnected hexagons, each representing a key facet of UX. These facets include: Usefulness, Usability (how easy, effective, and efficient the product is in helping users achieve their objectives), Desirability (the appeal a product holds for the users), Findability (how easily users can find, navigate, and access the information or features), Accessibility (the extent to which a product can be used by people with diverse abilities, including those with disabilities), Credibility (the degree to which users trust the product and the information it provides), and Value (the meaningful benefits the product delivers to users and stakeholders) (Morville 2004).
Morville’s Honeycomb Model underscores the importance of harmonising these facets to create a successful and engaging UX. It serves as a qualitative measurement tool, which is especially useful in the early design stages to ensure that no aspect is overlooked (Lee & Kim 2017).
Research methods and design
A DSR strategy was identified as the most suitable approach for developing chatbot design principles to enhance the user experience of LMSs in higher education. Design knowledge involves understanding the relationship between problem and solution spaces while ensuring the reusability of technology across various scenarios, users and time points (Möller, Guggenberger & Otto 2020; Wache et al. 2022).
A five-phase iterative DSR process, as suggested by Vaishnavi and Kuechler (2008), was followed in this study, progressing from problem awareness to conclusion. The phases of this process are illustrated in Figure 2. Problem awareness involves the gathering of information to become aware of the problem and to get an understanding of it. The Suggestion phase contributes towards a solution by suggesting objectives of a potential solution. The next step (Development) involves the development of the solution whereas evaluation of the solution is done in the last phase. Note that this is an iterative process. The DSR process is concluded by communicating the results of the process. (Vaishnavi & Kuechler 2008).
 |
FIGURE 2: Design science research process steps or phases. |
|
Awareness
During the awareness phase, the researcher conducted a comprehensive exploration to understand the research problem, identify challenges, and determine gaps and inefficiencies in the existing landscape. This phase highlighted a significant gap: the absence of comprehensive guidelines in empirical research for designing and developing LMS chatbots. The data collection methods included personal experiences, informal discussions with other users and a literature review. Anecdotal evidence from first-hand or second-hand reports provided valuable insights into the real-life issues faced by service providers.
Suggestion
This phase draws on the existing literature on design principles and features. The need for these principles emerged during the awareness phase of this research, where empirical evidence highlighted gaps in LMS chatbot guidelines. To address these gaps, the proposed design principles were formulated based on the existing literature and were enriched thereby. Additionally, Morville’s (2004) UX Honeycomb Model was integrated to ensure a holistic approach to UX enhancement.
Development
A Design Thinking workshop was initiated by the researcher, as part of the third phase of the study, conducted on 25 May 2023 at the University of Pretoria, Hatfield Campus, with 12 participants drawn from diverse South African higher education contexts. The participants included four students, four lecturers and four LMS administrators (which included the scope of instructional designers, technical support staff and curriculum developers) from both public and private institutions, as well as universities of technology and traditional universities. Using their diverse perspectives, the team created a basic prototype chatbot using Figma software. As regular LMS users, they provided critical insights into the design, functionality and user experience of an LMS-integrated chatbot, highlighting its potential to improve responsiveness, accessibility and the overall learning experience. The data collection methods included Figma screenshots, observations and field notes. The researcher conducted non-participatory observations from an adjoining room, separated by a one-way glass window, to maintain an impartial perspective and gather rich qualitative data. This approach documented the practical application of the five stages of design thinking developed by the Hasso Plattner Institute of Design at Stanford University (see Figure 3) (Meinel et al. 2022). Using their diverse perspectives, the team created a basic prototype chatbot using Figma software. It is important to note that this prototype served only as the visualisation of a potential LMS chatbot and not as the final design artefact. The design thinking workshop served as a dynamic platform for data collection, aligning with the principles of The Hasso Plattner Institute of Design at Stanford University (Meinel et al. 2022). The workshop provided a better understanding of the context and practical needs identified in the literature regarding UX in the LMS environment (Parizi et al. 2022). The data collected on tentative design principles is presented in Table 2.
 |
FIGURE 3: Participant worksheet 1 – Interview with a student. |
|
| TABLE 2: Schema-Based Example of Design Principle 1. |
Design thinking workshop outputs
The design thinking workshop outputs were analysed using elements of the UX Honeycomb Model, focusing on end-user perspectives, tasks, objectives and challenges within the LMS user journey. Data sources included transcripts, observations, participant worksheets and Figma screenshots. These informed the development of a design artefact that embodies a tentative set of design principles. While the design principles aimed to tailor chatbot development to the specific needs of LMS users, a data analysis using a Constant Comparative Analysis method (CCA) revealed broader, overarching requirements related to features and functionalities that could be effectively addressed through chatbot implementation.
By combining the findings from the design thinking workshop with the proposed design principles formulated during the suggestion phase, a set of tentative design principles was developed. Each design principle was structured according to the following components: implementer, aim, and user; context; mechanisms; subsidiary components or artefacts; and rationale (see Table 2).
Evaluation
During this phase, feedback on the tentative design principles was gathered using a questionnaire from four experts in LMS design. These experts were presented with a real-life LMS chatbot, specifically the Blackboard Chatbot (Anthology Inc. 2023), to illustrate the application of some of the design principles and identify any missing elements. The Blackboard Chatbot, available to Software as a Service (SaaS) clients in North America with certain features activated, provided a practical context for evaluating the principles. Permission from Blackboard was granted to allow the experts access to the system, which enhanced the real-world relevance of the evaluation. The focus of the evaluation was on refining the tentative design principles, rather than on assessing the chatbot itself. The real-life chatbot served as a tool to demonstrate the principles in action and to pinpoint areas where the principles could be better implemented or further developed.
The first section of the questionnaire presented Likert-type questions, which were directly associated with the tentative design principles outlined in Table 3. Each question evaluated the importance of the specific design principle as perceived by the expert.
| TABLE 3: Tentative set of design principles mapped with the user experience Honeycomb Model. |
Expert evaluations of the tentative LMS chatbot design principles yielded both qualitative insights and quantitative ratings that were instrumental in refining the final framework. The experts emphasised that features such as responsive interaction and focused conversation are critical for delivering timely, relevant information while effectively managing user expectations. They noted that including opt-out functionality and using an appropriate tone enhances user autonomy and engagement. Additionally, the evaluations highlighted the importance of progress tracking, personalised recommendations, and robust privacy and error-handling measures – including human-agent handover – to build trust and ensure seamless interactions.
The ‘Conclusion’ phase involved articulating the research findings as a set of design principles to be presented in an academic paper. This phase not only expands the existing knowledge base within the Information Systems discipline but also provides actionable guidance for practitioners in the field of LMS design.
The final set of design principles
After applying the CCA method and analysing the data from the design thinking workshop and the expert evaluations, the researcher refined the final LMS chatbot design principles by reducing them from 17 to 10 principles. Table 4 compares the tentative set of design principles detailed in Table 3 (first column) with the final refined set (second column).
| TABLE 4: Final set of design principles compared to the suggested set of design principles. |
By categorising the design principles (Table 5), as suggested by Expert 2, specific aspects relating to technical mechanisms, language, UX and feedback mechanisms become clearer. As Expert 2 noted, ‘You could consider grouping principles: e.g. technical, language, user experience, feedback’. This structured classification not only clarifies overlapping principles, some of which span multiple categories, but also enhances the accessibility and applicability of the design framework. It supports stakeholders and implementers in navigating key considerations more effectively.
| TABLE 5: Categorised final set of learning management system chatbot design principles. |
Scientific rigour
To ensure scientific rigour, the study adopted reflexivity and positionality measures, acknowledging the influence of the researcher’s professional background and assumptions on the research process. Pragmatism recognises that cultural and personal perspectives can shape how findings are observed, interpreted and reported, and that the researcher’s values play a role in this interpretation (Tashakkori & Teddlie 2010). As a qualitative researcher within a pragmatic worldview, the author’s experiences in higher education guided the study towards practical, contextually relevant outcomes through actionable design principles. Awareness of personal assumptions, combined with rich contextualisation, inclusion of participant perspectives and transparent documentation of the analysis process, strengthened the trustworthiness and dependability of the study, ensuring that findings accurately reflected participants’ experiences and the research context (Patton 2001; Rolfe 2006).
Credibility was further enhanced through methodological triangulation, incorporating multiple data sources and methods, including input from LMS users and experts, observations, participant worksheets, Figma screenshots and audio recordings. Verification of transcripts against recordings and repeated readings ensured accuracy, while systematic application of the CCA method allowed the identification of overarching requirements and refinement of design principles. Collectively, these measures ensured that the study maintained high standards of rigour while producing contextually relevant and actionable findings.
Ethical considerations
This study was approved by the Research Ethics Committee of the Faculty of Engineering, Built Environment and Information Technology at the University of Pretoria (Ref. No. EBIT/246/2022). Ethical clearance was obtained in accordance with the University’s guidelines, which emphasise voluntary participation, informed consent, and the protection of participant privacy and confidentiality.
The recruitment of participants for the design thinking workshop was conducted purposively by the researcher. Participants were selected based on their active engagement with LMS and their professional roles within higher education institutions, ensuring that they possessed relevant experience and insights into the design, functionality and user experience of LMS-integrated chatbots. Recruitment was carried out directly by the researcher via email invitations, without the involvement of an independent recruiter. Prior to participation, all individuals were provided with an invitation letter outlining the study’s purpose, data collection instruments and intended use of the findings. Written informed consent was obtained from all participants before the commencement of the data collection. Participants were further informed of their right to decline participation at any stage without consequence, and that no incentives would be offered to induce participation.
To protect anonymity, the participants’ real names were concealed and replaced with pseudonyms on all transcripts and data records. Confidentiality was ensured by restricting access to identifying information to the researcher only. All collected data were securely archived at the University of Pretoria in an organised and retrievable format to ensure an audit trail and to facilitate future access, if required. The researcher maintained sensitivity and respect throughout the process to minimise any potential emotional discomfort. She also clarified that the research was conducted purely for academic purposes.
Discussion
The findings align with prior research on user motivations and preferences related to chatbot utilisation, while extending understanding by providing a structured, empirically grounded set of design principles for LMS-integrated chatbots. These principles build on previous studies by incorporating elements of technical functionality, language considerations, UX, privacy, pedagogical alignment and personalised learning. Their broad applicability across diverse higher education institutions addresses a critical gap in LMS chatbot development, offering both a holistic framework and actionable guidance for practitioners.
The final set of design principles suggests that chatbots should integrate both pragmatic and hedonic attributes, particularly where flexibility is feasible. The integration of Natural Language Processing (NLP) techniques, consistent with Bezverhny et al. (2020), enhances the chatbot’s ability to comprehend user queries naturally, resulting in fluid and intuitive interactions. Engaging visual elements, 24/7 availability, multilingual support and context-aware responses further contribute to a more inclusive learning experience, supporting diverse user needs and preferences while ensuring seamless integration into LMS platforms.
These principles also emphasise scalability, ethical considerations and user-centred design. As shown in Table 5, they align with prior research on educational chatbots, including Kuhail et al. (2023), who emphasise adaptability, and Hobert and Berens (2023), who highlight pedagogical alignment. By integrating these considerations, the study provides a comprehensive approach to enhancing LMS chatbot user experience across multiple HEI contexts.
This study makes a significant contribution by bridging the research gap in LMS chatbot design and providing practitioners with actionable, empirically grounded guidelines. Drawing on the unique insights of a researcher who is simultaneously a student, instructor and academic, the work empathetically addresses the multifaceted challenges faced by both learners and educators. It underscores the critical importance of seamless integration and responsive interactions within LMS platforms. These are essential for mitigating user frustrations and delivering immediate, yet humanised support. Furthermore, the study advocates for LMS platforms empowered by an adaptable chatbot that not only offers instant problem resolution but also extends emotional and mental health support, thereby meeting diverse user expectations in an increasingly connected global environment.
Conclusion, limitation and future research
This study provides empirically grounded design principles for LMS-integrated chatbots, offering actionable guidance to enhance responsiveness, accessibility, personalisation and trust. By improving user experience and supporting inclusive, student-centred learning, these principles contribute directly to the digital transformation of higher education, helping institutions create more engaging and equitable technology-enhanced learning environments.
Limitations include potential biases from participants’ prior experiences or perceptions of the LMS, which may have influenced their contributions. The Blackboard Chatbot (Anthology Inc. 2023) used in expert evaluation was not built using the proposed principles, yet it provided a practical reference for assessment. While generative AI chatbots like ChatGPT operate outside LMS platforms, the principles are expected to be applicable for customised LLM-driven LMS chatbots.
Future research should explore the integration of emotional and inclusive design frameworks, such as Hassenzahl’s Hedonic-Pragmatic Model (2007), to foster trust, minimise frustration and support diverse user needs. Implementing these principles will ensure that LMS chatbots remain adaptable, ethically grounded and aligned with evolving expectations, advancing digital transformation and promoting more engaging, inclusive and student-centred higher education.
Acknowledgements
The authors would like to acknowledge the time and effort invested by the design team in contributing to the formulation of the design principles presented in this article.
This article is partially based on Maria M. Swanepoel’s doctoral dissertation, ‘Enhancing Users’ Experience of a Learning Management System within Higher Education: Chatbot Design Principles for Service Providers’, submitted in fulfilment of the requirements for the degree of Doctor of Philosophy in Information Technology (Information Systems) at the Department of Informatics, Faculty of Engineering, Built Environment and Information Technology, University of Pretoria, South Africa, on 02 September 2024. The dissertation was supervised by Machdel Matthee and Marie J. Hattingh.
Competing interests
The authors declare that they have no financial or personal relationships that may have inappropriately influenced them in writing this article.
CRediT authorship contribution
Maria M. Swanepoel: Conceptualisation, Data curation, Formal analysis, Investigation, Methodology, Project administration, Resources, Visualisation, Writing – original draft, Writing – review & editing. Machdel Matthee: Supervision, Writing – review & editing. Marie J. Hattingh: Supervision, Writing – review & editing. All authors reviewed the article, contributed to the discussion of results, approved the final version for submission and publication, and take responsibility for the integrity of its findings.
Funding information
This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.
Data availability
The data that support the findings of this study are available from the corresponding author, Maria M. Swanepoel, upon reasonable request.
Disclaimer
The views and opinions expressed in this article are those of the authors and are the product of professional research. It does not necessarily reflect the official policy or position of any affiliated institution, funder, agency or that of the publisher. The authors are responsible for this article’s results, findings and content.
References
Al-Handhali, B., Al-Rasbi, A. & Sherimon, P., 2020, ‘Advantages and disadvantages of Learning Management System (LMS) at AOU Oman’, International Journal of Technology 1(2), 222–228.
Al-Sharhan, S., Al-Hunaiyyan, A., Alhajri, R. & Al-Huwail, N., 2020, ‘Utilization of Learning Management System (LMS) among instructors and students’, in Z. Zakaria & R. Ahmad (eds.), Advances in Electronics Engineering: Proceedings of the ICCEE 2019, Lecture Notes in Electrical Engineering, vol. 619, pp. 15–23, Springer, Singapore. https://doi.org/10.1007/978-981-15-1289-6_2
Allam, H., Dempere, J., Kalota, F. & Hua, D., 2024, ‘Enhancing educational continuity: Exploring factors affecting the success of learning management systems in Dubai higher education’, Frontiers in Education 9, a1382021. https://doi.org/10.3389/feduc.2024.1382021
Almusharraf, A.I., 2024, ‘An investigation of university students’ perceptions of learning management systems: Insights for enhancing usability and engagement’, Sustainability 16(22), a10037. https://doi.org/10.3390/su162210037
Anthology Inc., 2023, Help centre, Blackboard, viewed 21 May 2025, from https://help.blackboard.com/Learn/Administrator/SaaS/Tools_Management/Chatbot_for_Learn.
Asenahabi, B.M., Peters, A.I. & Nambiro, A.W., 2022, ‘Evaluating learning management system usability level towards online learning: University students’ perspective’, International Journal of Computer Trends and Technology 70(12), 12–20. https://doi.org/10.14445/22312803/IJCTT-V70I12P102
Az-Zahra, H.M., Nurhayati, D. & Herlambang, A.D., 2023, ‘User experience in learning management system: Edmodo versus Google Classroom’, Journal of Information Technology and Computer Science 7(3), 196–208. https://doi.org/10.25126/jitecs.73383
Benke, I., 2020, ‘Towards design principles for trustworthy affective chatbots in virtual teams’, in Proceedings of the 28th European Conference on Information Systems (ECIS 2020), Marrakesh, viewed 19 May 2025, from https://aisel.aisnet.org/ecis2020_rip/41/.
Bezverhny, E., Dadteev, K., Barykin, L., Nemeshaev, S. & Klimov, V., 2020, ‘Use of chat bots in learning management systems’, Procedia Computer Science 169, 652–655. https://doi.org/10.1016/j.procs.2020.02.195
Chaskopoulos, D., Hægdahl, J., Sagvold, P., Trinquet, C. & Edal, M., 2022, ‘Implementing a chatbot solution for learning management system’, arXiv preprint. https://doi.org/10.48550/arXiv.2206.13187
Chen, B., 2019, ‘Designing for networked collaborative discourse: An UnLMS approach’, TechTrends 63(2), 194–201. https://doi.org/10.1007/s11528-018-0284-7
Chen, Y., Jensen, S., Albert, L., Gupta, S. & Lee, T., 2023, ‘Artificial intelligence (AI) student assistants in the classroom: Designing chatbots to support student success’, Information Systems Frontiers 25, 161–182. https://doi.org/10.1007/s10796-022-10291-4
Cozlov, V. & Zadorojnii, M., 2022, ‘Inclusivity and accessibility in UX design’, in Proceedings of the Technical Scientific Conference of Undergraduate, Master and PhD Students, Technical University of Moldova, Chisinau, Republic of Moldova, March 29–31, 2022, vol. I, pp. 385–388.
Demir, F., Bruce-Kotey, C. & Alenezi, F., 2022, ‘User experience matters: Does one size fit all? Evaluation of learning management systems’, Technology, Knowledge and Learning 27, 49–67. https://doi.org/10.1007/s10758-021-09518-1
Desmet, P. & Hekkert, P., 2007, ‘Framework of product experience’, International Journal of Design 1(1), 57–66. https://doi.org/10.1016/B978-008045089-6.50003-4
Feine, J., Morana, S. & Maedche, A., 2020, ‘Designing interactive chatbot development systems’, in Proceedings of the 41st International Conference on Information Systems (ICIS 2020), Association for Information Systems, Hyderabad, India, December 13–16, 2020.
Fleming, T., 2023, ‘Does your eLearning content need to be accessible?’, Tovuti LMS Blog, viewed from https://www.tovutilms.com/blog/elearning-accessibility.
Gregor, S., Chandra Kruse, L. & Seidel, S., 2020, ‘Research perspectives: The anatomy of a design principle’, Journal of the Association for Information Systems 21(6), 1622–1652. https://doi.org/10.17705/1jais.00649
Guo, Y., Wang, J., Wu, R., Li, Z. & Sun, L., 2022, ‘Designing for trust: A set of design principles to increase trust in chatbot’, CCF Transactions on Pervasive Computing and Interaction 4(4), 474–481. https://doi.org/10.1007/s42486-022-00106-5
Hassenzahl, M., 2007, ‘The hedonic/pragmatic model of user experience’, Towards a UX Manifesto 10, 2007.
Hassenzahl, M., 2008, ‘User experience (UX): Towards an experiential perspective on product quality’, in E. Brangier, G. Michel, J.M.C. Bastien & N. Carbonell (eds.), Proceedings of the 20th Conference on l’Interaction Homme-Machine (IHM ‘08), Metz, France, ACM, New York, NY, September 2–5, 2008, pp. 11–15.
Heng, L., Yuen, P., Fui, Y. & Muniandy, M., Sangodiah, A. & Ping, Y.Y., 2022, ‘Adaptive learning content based on learning styles in learning management system’, in F. Saeed, T. Al-Hadhrami, E. Mohammed & M. Al-Sarem (eds.), Advances on smart and soft computing, advances in intelligent systems and computing, vol. 1399, pp. 3–11, Springer, Singapore. https://doi.org/10.1007/978-981-16-5559-3_1
Hobert, S. & Berens, F., 2023, ‘Developing a digital tutor as an intermediary between students, teaching assistants, and lecturers’, Educational Technology Research and Development 72(2), 1–23. https://doi.org/10.1007/s11423-023-10293-2
Ibrahim, E. & Aziz, E., 2022, ‘Exploring the user experience (UX) of university learning management system (LMS)’, International Journal of Academic Research in Progressive Education and Development 11(3), 391–403. https://doi.org/10.6007/IJARPED/v11-i3/14454
Ifelebuegu, A., Kulume, P. & Cherukut, P., 2023, ‘Chatbots and AI in education (AIEd) tools: The good, the bad, and the ugly’, Journal of Applied Learning and Teaching 6(2), 1–24. https://doi.org/10.37074/jalt.2023.6.2.29
International Organization for Standardization (ISO), 2010, ISO 9241-210:2010 Ergonomics of human-system interaction – Part 210: Human-centred design for interactive systems, ISO, Geneva.
Jei, T., Al-Rahili, R. & Al-Farani, L., 2024, ‘The effectiveness of chatbots in developing scientific research skills and motivation for learning among postgraduate students’, International Journal of Educational Sciences and Arts 3(2), 96–128. https://doi.org/10.59992/IJESA.2024.v3n2p4
Jung, H., Lee, J. & Park, C., 2020, ‘Deriving design principles for educational chatbots from empirical studies on human-chatbot interaction’, Journal of Digital Contents Society 21(3), 487–493. https://doi.org/10.9728/dcs.2020.21.3.487
Kim, N.-H., 2020, ‘User experience validation using the honeycomb model in the requirements development stage’, International Journal of Advanced Smart Convergence 9(3), 227–231.
Kuhail, M., Alturki, N., Alramlawi, S. & Alhejori, K., 2023, ‘Interacting with educational chatbots: A systematic review’, Education and Information Technologies 28(1), 973–1018. https://doi.org/10.1007/s10639-022-11177-3
Lamo, P., Perales, M. & De-la-Fuente, L., 2022, ‘Case study in online course of computer engineering during COVID-19 pandemic’, Electronics 11(4), 1–18. https://doi.org/10.3390/electronics11040578
Lee, M.S. & Kim, S.H., 2017, ‘Factors affecting the use of the intelligent chatbot services’, Journal of Service Research and Studies 7(3), 37–55.
Lima, M., Brito, G. & Caldeira, E., 2019, ‘Preference of the use of Moodle as a learning management system in Brazilian universities’, International Journal of Learning and Teaching 5(4), 301–305. https://doi.org/10.18178/ijlt.5.4.301-307
Liu, H., Moparthi, D., Angrave, L., Amos, J., Dalpiaz, D., Vogiatzis, C. et al., 2022, ‘Understanding the needs of students with and without disabilities for inclusive UDL-based design of engineering courses through learning management systems’, in 2022 ASEE Annual Conference and Exposition, American Society for Engineering Education, Minneapolis, MN, June 26–29, 2022. https://doi.org/10.18260/1-2--37361
Macayaon, R. & Palomares, N., 2023, ‘Students’ LMS experience and their learning motivation and academic performance in mathematics’, International Journal of Arts, Sciences and Education 4(2), 70–96.
Maslov, I., Nikou, S. & Hansen, P., 2021, ‘Exploring user experience of learning management system’, International Journal of Information and Learning Technology 38(4), 344–363. https://doi.org/10.1108/IJILT-03-2021-0046
Meinel, C., Willems, C., Staubitz, T., Sauer, D. & Hagedorn, C., 2022, OpenHPI: 10 years of MOOCs at the Hasso Plattner Institute, Universitätsverlag Potsdam, Potsdam. https://doi.org/10.25932/publishup-56020
Mendoza, S., Sánchez-Adame, L., Urquiza-Yllesca, J., González-Beltrán, B. & Decouchant, D., 2022, ‘A model to develop chatbots for assisting the teaching and learning process’, Sensors 22(15), 1–21. https://doi.org/10.3390/s22155532
Möller, F., Guggenberger, T. & Otto, B., 2020, ‘Towards a method for design principle development in information systems’, in S. Hofmann, O. Müller & M. Rossi (eds.), Designing for digital transformation. Co-creating services with citizens and industry – DESRIST 2020, Kristiansand, Norway, Proceedings, Lecture Notes in Computer Science, Springer, Cham, December 2–4, 2020, vol. 12388, pp. 208–220. https://doi.org/10.1007/978-3-030-64823-7
Morville, P., 2004, User experience design, Semantic Studio, viewed 19 May 2025 from http://semanticstudios.com/user_experience_design/.
Parizi, R., Prestes, M., Marczak, S. & Conte, T., 2022, ‘How has design thinking been used and integrated into software development activities? A systematic mapping’, Journal of Systems and Software 187, 1–24. https://doi.org/10.1016/j.jss.2022.111217
Patton, M., 2001, Qualitative evaluation and research methods, 3rd edn., Sage, Thousand Oaks, CA.
Ramandanis, D. & Xinogalos, S., 2023, ‘Designing a chatbot for contemporary education: A systematic literature review’, Information 14(9), 503. https://doi.org/10.3390/info14090503
Ramesh, K., Vermette, L. & Chilana, P., 2021, ‘Setting up, troubleshooting, and innovating on the delivery of online instruction: A case study of an LMS Q&A forum’, in Proceedings of the 8th ACM Conference on Learning @ Scale (L@S ‘21), Virtual Event, Germany, Association for Computing Machinery, New York, NY, June 22–25, 2021, pp. 59–67. https://doi.org/10.1145/3430895.3460133
Rane, N., 2023, ‘Chatbot-enhanced teaching and learning: Implementation strategies, challenges, and the role of ChatGPT in education’, Challenges, 21 July, viewed 03 December 2025, from https://www.mdpi.com/journal/challenges.
Rocio, V. & Wesley, A., 2020, ‘Building a chatbot for student support’, Revista de Ciências da Computação 5(15), 103–114.
Rolfe, G., 2006, ‘Validity, trustworthiness and rigour: Quality and the idea of qualitative research’, Journal of Advanced Nursing 53(3), 304−310. https://doi.org/10.1111/j.1365-2648.2006.03727.x
Saleh, A., Abuaddous, H., Alansari, I. & Enaizan, O., 2022, ‘The evaluation of user experience of learning management systems using UEQ’, International Journal of Emerging Technologies in Learning 17(7), 145–162. https://doi.org/10.3991/ijet.v17i07.29525
Saroia, A. & Gao, S., 2019, ‘Investigating university students’ intention to use mobile learning management systems in Sweden’, Innovations in Education and Teaching International 56(5), 569–580. https://doi.org/10.1080/14703297.2018.1557068
Sesay, G.A. & Sesay, I.M., 2024, ‘Internal quality control and the role of Learning Management Systems (LMS) in higher education institutions in Sierra Leone: Then, now, and later’, Education Journal 13(5), 294–301. https://doi.org/10.11648/j.edu.20241305.16
Simon, P.D., Jiang, J., Fryer, L.K., King, R.B. & Frondozo, C.E., 2024, ‘An assessment of learning management system use in higher education: Perspectives from a comprehensive sample of teachers and students’, Technology, Knowledge and Learning 30, 1–27. https://doi.org/10.1007/s10758-024-09734-5
Slater, A., 2022, ‘Chatbots: Cybernetic psychology and the future of conversation’, Journal of Cinema and Media Studies 61(4), 181–187. https://doi.org/10.1353/cj.2022.0036
Stoesz, B.M. & Niknam, M., 2022, ‘Student perceptions of the visual design of learning management systems’, Canadian Journal of Learning and Technology 48(3), 1–22. https://doi.org/10.21432/cjlt28154
Swanepoel, M., Matthee, M., Hattingh, M. & Weilbach, L., 2024 ‘Enhancing UX in learning management systems: Leveraging design thinking for the development of Chatbot design principles’, in ICT education: 53rd Annual Conference of the Southern African Computer Lecturers’ Association (SACLA 2024), Gqeberha, July 17–19, 2024, Revised Selected Papers, p. 132.
Tashakkori, A. & Teddlie, C., 2010, SAGE handbook of mixed methods in social and behavioral research, 2nd edn., SAGE, Thousand Oaks.
Turnbull, D., Chugh, R. & Luck, J., 2023, ‘Learning management systems and social media: A case for their integration in higher education institutions’, Research in Learning Technology 31, 2814. https://doi.org/10.25304/rlt.v31.2814
Vaishnavi, V. & Kuechler, W., 2008, Design science research methods and patterns: Innovating information and communication technology, 1st edn., Auerbach Publications, Boca Raton, FL.
Vandeyar, T., 2020, ‘The academic turn: Social media in higher education’, Education and Information Technologies 25(6), 5617–5635. https://doi.org/10.1007/s10639-020-10240-1
Wache, H., Möller, F., Schoormann, T., Strobel, G. & Petrik, D., 2022, ‘Exploring the abstraction levels of design principles: The case of chatbots’, in Proceedings of the 17th International Conference on Wirtschaftsinformatik (WI 2022), Association for Information Systems, Nürnberg, Germany, February 21–23, 2022.
Walraven, Y.E., 2024, ‘From goals to growth? Chatbot feedback on learner goals and action plans’, Bachelor’s thesis, University of Twente.
Wenzel, A. & Moreno, J., 2022, ‘Designing and facilitating optimal LMS student learning experiences: Considering students’ needs for accessibility, navigability, personalization, and relevance in their online courses’, Northwest eLearning Journal 2(1), 1–35. https://doi.org/10.5399/osu/nwelearn.2.1.5642
Yawisah, U., Akla, A., Umam, A., Asad, M. & Wahyudin, W., 2022, ‘The implications of learning management system on education quality in the new normal era: Evidence from Islamic higher education’, Journal of Social Studies Education Research 13(2), 147–169.
|
Hide
Show all
Email this article (Login required)
