2014 e learning innovations conference maina muuro keynoteaddress 31st_july_2014
1 like406 views
Elizaphan Muuro Maina presented on integrating artificial intelligence systems into e-learning. He discussed how AI can enable adaptive learning, personalized learning, and AI tutors. As an example, he described how an intelligent grouping algorithm using data mining techniques can automatically group students in Moodle for collaborative learning based on their collaboration competence levels clustered from forum activity data. The integration of AI has the potential to advance personalized and adaptive e-learning.
2014 e learning innovations conference maina muuro keynoteaddress 31st_july_2014
- 1. 18/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 2. PRESENTER Elizaphan Muuro Maina Lecturer Kenyatta University Department of Computing And Information Technology PhD Student in University of Nairobi (Computer Science : Intelligent Systems) 28/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 3. Integration of Artificial Intelligence Systems in e-learning • Why • Era of Cognitive Computing – E-learning platforms • Adaptive learning • Personalized learning • A.I Tutors • Example – Collaborative learning in Moodle • Intelligent grouping algorithm 38/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 4. Era of Cognitive Computing • New era in IT: – Computing systems that will understand the world in the way that humans do: through senses, learning, and experience. – E.g. IBM Watson • System generate a lot of data. • What can we do with it? – Data mining: • Statistical analysis • Classification • Clustering • Prediction • Visualization • Need to do a paradigms shift to intelligent e-learning platforms 48/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 5. Adaptive e-learning systems (AeLS) • The aim of adaptive e-Learning is to provide the students the appropriate content at the right time, means that the system is able to determine the knowledge level, keep track of usage, and arrange content automatically for each student for the best learning result. • Two types: • Adaptivity: System which initiates, system adjust its presentation according to the student characteristics automatically, • Adaptability: Student who initiates, capability of the system to support user adjustment • Example • Based on student Learning Styles 58/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 6. References Surjono, H. D. (2014). The Evaluation of a Moodle Based Adaptive e-Learning System. International Journal of Information & Education Technology, 4(1). Esichaikul, V., Lamnoi, S., & Bechter, C. (2011). Student Modelling in Adaptive E-Learning Systems. Knowledge Management & E-Learning: An International Journal (KM&EL), 3(3), 342-355. 68/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 7. Personalized e-learning • Automatically adapt to the interests and levels of learners. – E.g. User profiling where user profile including interests, levels and learning patterns can be assessed during the learning process. Based upon the profile, personalized learning resource could be generated to match the individual preferences and levels. • Furthermore, learners with the common interests and levels can be grouped, and feedbacks of one person can serve as the guideline for information delivery to the other members within the same group. • These systems respond to the needs of the student, putting greater emphasis on certain topics, repeating things that students haven’t mastered, and generally helping students to work at their own pace, whatever that may be. 78/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 8. References • Lu, F., Li, X., Liu, Q., Yang, Z., Tan, G., & He, T. (2007). Research on personalized e-learning system using fuzzy set based clustering algorithm. In Computational Science–ICCS 2007 (pp. 587-590). Springer Berlin Heidelberg. • Gong, M. (2008, January). Personalized E-learning System by Using Intelligent Algorithm. In Knowledge Discovery and Data Mining, 2008. WKDD 2008. First International Workshop on (pp. 400-401). IEEE. • Li, X., & Chang, S. K. (2005, September). A Personalized E-Learning System Based on User Profile Constructed Using Information Fusion. In DMS (pp. 109-114). • Castro, F., Vellido, A., Nebot, À., & Mugica, F. (2007). Applying data mining techniques to e-learning problems. In Evolution of teaching and learning paradigms in intelligent environment (pp. 183-221). Springer Berlin Heidelberg. 88/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 9. A.I Tutors • Fewer instructors • Tutorial fellows are not there in e-learning • Need for A.I tutors • Intelligent tutoring systems 98/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 10. Example: Collaborative learning in Moodle • Social constructivist pedagogy (Vygotsky ,1978) • The learning systems in particularly have shifted from normal paradigms to more social constructionist • Moodle e-learning platform: – Forums: Students can participate in group discussion – Wikis: Students can create wiki page and come up with a group product or edit content as a group – Chats: Chats rooms for student to meet and exchange ideas. – Workshops: Students can engage in a peer assessment activity 108/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 11. Data mining in Moodle • LAMS- Moodle • Weka Jar lib- Clustering Agorithms (Skmeans and EM): http://www.cs.waikato.ac.nz/ml/weka/downl oading.html 118/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 12. Implementation • Moodle 2.4 was installed on the Windows Server • Weka Jar lib was added to the Windows Server • Weka Jar lib was invoked from the Moodle PHP code • Preprocessing the Moodle forum Data • The summary table is stored as text file with .cvs extension and it has the following columns: • User id(taken from mdl_role_assignments by checking the role and enroll conditions) • Number of posts (taken from mdl_forum_posts) • Number of replies(taken from mdl_forum_posts) • Forum ratings(taken from mdl_rating) • This summary table is fed as an input to the Weka.php program which has the clustering algorithms. • Applying clustering algorithms to create collaboration competence levels 128/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 13. Example • Applying clustering algorithms to create collaboration competence levels • 3 Clusters: • Cluster O • Cluster 1 • Cluster 2 • Create heterogeneous groups • Ranked Array • IGCC algorithm picks students from different collaborative levels as per the rank and assigns them to one group • Group data into Moodle tables 138/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014
- 14. Interesting research areas in A.I and e-learning • Text analysis • Yet to be realized in e-learning platforms 148/16/2014 E.Maina: eLearning Innovations Conference & Expo 29th-31st july 2014