Date of Award
Doctor of Philosophy (PhD)
Dr Elarbi Badidi
Dr. Amir Ahmad
Personalization has proved to achieve better learning outcomes by adapting to specific learners’ needs, interests, and/or preferences. Traditionally, most personalized learning software systems focused on formal learning. However, learning personalization is not only desirable for formal learning, it is also required for informal learning, which is self-directed, does not follow a specified curriculum, and does not lead to formal qualifications. Wikis among other informal learning platforms are found to attract an increasing attention for informal learning, especially Wikipedia. The nature of wikis enables learners to freely navigate the learning environment and independently construct knowledge without being forced to follow a predefined learning path in accordance with the constructivist learning theory. Nevertheless, navigation on information wikis suffer from several limitations. To support informal learning on Wikipedia and similar environments, it is important to provide easy and fast access to relevant content. Recommendation systems (RSs) have long been used to effectively provide useful recommendations in different technology enhanced learning (TEL) contexts. However, the massive diversity of unstructured content as well as user base on such information oriented websites poses major challenges when designing recommendation models for similar environments. In addition to these challenges, evaluation of TEL recommender systems for informal learning is rather a challenging activity due to the inherent difficulty in measuring the impact of recommendations on informal learning with the absence of formal assessment and commonly used learning analytics. In this research, a personalized content recommendation framework (PCRF) for information wikis as well as an evaluation framework that can be used to evaluate the impact of personalized content recommendations on informal learning from wikis are proposed. The presented recommendation framework models learners’ interests by continuously extrapolating topical navigation graphs from learners’ free navigation and applying graph structural analysis algorithms to extract interesting topics for individual users. Then, it integrates learners’ interest models with fuzzy thesauri for personalized content recommendations. Our evaluation approach encompasses two main activities. First, the impact of personalized recommendations on informal learning is evaluated by assessing conceptual knowledge in users’ feedback. Second, web analytics data is analyzed to get an insight into users’ progress and focus throughout the test session. Our evaluation revealed that PCRF generates highly relevant recommendations that are adaptive to changes in user’s interest using the HARD model with rank-based mean average precision (MAP@k) scores ranging between 100% and 86.4%. In addition, evaluation of informal learning revealed that users who used Wikipedia with personalized support could achieve higher scores on conceptual knowledge assessment with average score of 14.9 compared to 10.0 for the students who used the encyclopedia without any recommendations. The analysis of web analytics data show that users who used Wikipedia with personalized recommendations visited larger number of relevant pages compared to the control group, 644 vs 226 respectively. In addition, they were also able to make use of a larger number of concepts and were able to make comparisons and state relations between concepts.
Ismail, Heba M, "A Framework for Personalized Content Recommendations to Support Informal Learning in Massively Diverse Information WIKIS" (2019). Dissertations. 82.