Artificial Intelligence and Persuasive Computing Approach for Motivating Students and Enhancing their Learning Experience
Bibliographic record
Abstract
Computing technologies offer promising approaches that could be leveraged to improve education and learning globally. Online educational systems, including learning management systems (LMS), have transformed education at all levels by making learning resources and services more accessible to diverse students across various levels of education. Universities widely employ LMS to deliver learning materials and resources to students. Recognizing that lectures alone may not be sufficient for deep understanding; students are encouraged to actively engage with the provided content and resources to acquire the necessary knowledge and skills. However, sustaining students’ motivation and engagement over time has become one of the largest barriers to effective learning with the systems. Without sustained motivation, students may disengage, leading to poor learning outcomes and diminished educational experiences. Identifying strategies that promote continuous motivation and meaningful student engagement is critical to unlocking the full potential of LMS and ensuring long-term educational success. Artificial intelligence (AI) and persuasive technology (PT) present elegant solutions that can be employed to make online educational systems more motivating and engaging for students to sustain them in achieving desired learning goals. An interesting aspect of the AI approach is that the learning states of students can be modelled in real-time based on their learning behaviour without distraction to their learning, and this will enable personalized interventions to be tailored to their needs. PT, on the other hand, leverages motivational appeals (such as self-monitoring, social comparison, and competition) in sustaining students’ engagement to achieve their learning goals. To contribute to improving online educational systems to better motivate students and enhance their learning experience, I explored AI techniques and motivational appeals of PT strategies in supporting students' engagement in learning. My research involved several key components: First, using a dataset of 924 university students and the self-determination theory framework, I employed machine learning techniques to examine the impact of motivation dimensions on students’ study strategies and academic performance. Second, building on the findings from the previous study, I applied machine learning methods to analyze learning interaction logs from two different sources: 488 students’ data from an eBook platform and over 125,000 students’ data from massive open online courses. This analysis aimed to investigate the relationship between data-driven engagement measures and academic performance, as well as to model students' engagement levels using a data-driven approach. Third, in an empirical study with 628 university students, I investigated the effects of three PT strategies (social comparison, social learning, and competition) operationalized in system design and integrated into a learning management system for real-world university course on students’ engagement and academic performance. Fourth, I examined the persuasiveness of four PT strategies and developed models that explored their relationship with self-determination theory constructs. I also developed and evaluated persuasive messages based on three strategies: self-monitoring, commitment & consistency, and social comparison. Fifth, I developed machine learning models to predict students' motivation levels based on their tracked learning behaviour. I then applied the model and personalized persuasive intervention to investigate the potential of leveraging AI and personalized persuasive intervention in promoting student motivation and engagement in a real-world university course using an LMS. The results of my evaluations demonstrated that PT strategies effectively increased students' motivation and engagement. Personalized persuasive interventions and machine learning models demonstrated to be an effective approach for providing adaptive support tailored to students' learning contexts. These findings suggest that AI techniques and PT are viable approaches that can be incorporated into online educational systems to improve their effectiveness in motivating students and enhancing their learning experience.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".