A Recommender System for Videos Suggestion in a SPOC: A Proposed Personalized Learning Method
Adaptivity, personalization and recommendation techniques are classic solutions recommended by many specialists for providing successful learning experiences by offering suitable adaptation that satisfy the learning preferences and meet heterogeneous char
- PDF / 229,500 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 78 Downloads / 212 Views
Laboratory of Technological Information and Modelisation (LTIM), Faculty of Sciences Ben M’Sik, University Hassan II, Casablanca, Casablanca, Morocco [email protected], [email protected], [email protected] 2 Laboratory of Sciences, Information, Communication and Education Technology (LAPSTICE), Faculty of Sciences Ben M’Sik, Casablanca, Morocco [email protected] 3 Observatory of Research in Didactics and University Pedagogy (ORDIPU), University Hassan II, Casablanca, Casablanca, Morocco [email protected] 4 Laboratory of Analytical Chemistry and Physical Chemistry of Materials, Faculty of Sciences Ben M’Sik, Casablanca, Morocco
Abstract. Adaptivity, personalization and recommendation techniques are classic solutions recommended by many specialists for providing successful learning experiences by offering suitable adaptation that satisfy the learning preferences and meet heterogeneous characteristics of users. In the present paper, we propose a video recommender system across a Small Private Online Course (SPOC). We adopt a hybrid recommendation technique which consists on analyzing users’ video behavior while enrolling into a SPOC, estimating their interest in videos, finding learners with similar profile and finally recommending target user the same videos in which similar users are interested in. The proposed approach consist first on capturing and analyzing user’s video clickstream in order to construct a user profile with an implicit way to infer user’s interest in videos. Second, the unsupervised K-Means clustering algorithm is used to group users with similar video behavior into clusters. Finally, videos from similar profiles that could meet user’s interest can be recommended. Keywords: Adaptive learning Recommendation technique User profile Clustering Video clickstream analysis
SPOC
© Springer Nature Switzerland AG 2019 Y. Farhaoui and L. Moussaid (Eds.): ICBDSDE 2018, SBD 53, pp. 92–101, 2019. https://doi.org/10.1007/978-3-030-12048-1_12
A Recommender System for Videos Suggestion in a SPOC
93
1 Introduction The phenomenon of Massive open online courses (MOOCs) and Small Private Online Courses (SPOCS) are remarkably shaping online learning landscape especially in higher education [1]. However, heterogeneity of student profiles is a real challenge to the “one-size-fits-all” learning model provided by MOOCs or SPOCs [2, 3]. Personalization, adaptivity and recommendation techniques are known to offer great potential to overcome these challenges. These concepts are said to be able to increase learner satisfaction, to improve the learning process and to enable learners in finding relevant educational resources that best meet their personal preferences and needs [4–9]. In the last few years, these different approaches have invited growing interest in MOOCs [2, 10–17]. Therefore, technological advancements in a myriad of fields such as data mining, machine learning, techniques for managing big data, artificial intelligence have extended the use in the education field [18, 19]. In the
Data Loading...
