Guess you like: course recommendation in MOOCs

Recommending courses to online students is a fundamental and also challenging issue in MOOCs. Not exactly like recommendation in traditional online systems, students who enrolled the same course may have very different purposes and with very different backgrounds. For example, one may want to study "data mining" after studying the course of "big data analytics" because the former is a prerequisite course of the latter, while some other may choose "data mining" simply because of curiosity. Employing the complete data from XuetangX1, one of the largest MOOCs in China, we conduct a systematic investigation on the problem of student behavior modeling for course recommendation. We design a content-aware algorithm framework using content based users' access behaviors to extract user-specific latent information to represent students' interest profile. We also leverage the demographics and course prerequisite relation to better reveal users' potential choice. Finally, we develop a course recommendation algorithm based on the user interest, demographic profiles and course prerequisite relation using collaborative filtering strategy. Experiment results demonstrate that the proposed algorithm performs much better than several baselines (over 2X by MRR). We have deployed the recommendation algorithm onto the platform XuetangX as a new feature, which significantly helps improve the course recommendation performance (+24.6% by click rate) comparing with the recommendation strategy previously used in the system.

[1]  David E. Pritchard,et al.  Bringing student backgrounds online: MOOC user demographics, site usage, and online learning , 2013, EDM.

[2]  Daniel M. Russell,et al.  Student skill and goal achievement in the mapping with google MOOC , 2014, L@S.

[3]  James Bennett,et al.  The Netflix Prize , 2007 .

[4]  Carolyn Penstein Rosé,et al.  Social factors that contribute to attrition in MOOCs , 2014, L@S.

[5]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[6]  Katharina Reinecke,et al.  Demographic differences in how students navigate through MOOCs , 2014, L@S.

[7]  José Eduardo Ochoa Luna,et al.  Online Courses Recommendation based on LDA , 2014, SIMBig.

[8]  Pattie Maes,et al.  Social information filtering: algorithms for automating “word of mouth” , 1995, CHI '95.

[9]  Yu He,et al.  The YouTube video recommendation system , 2010, RecSys '10.

[10]  S. Rozendaal,et al.  Campus 2.0 , 2017 .

[11]  Carolyn Penstein Rosé,et al.  “ Turn on , Tune in , Drop out ” : Anticipating student dropouts in Massive Open Online Courses , 2013 .

[12]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[13]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[14]  S. B. Aher,et al.  Combination of machine learning algorithms for recommendation of courses in E-Learning System based on historical data , 2013, Knowl. Based Syst..

[15]  M. Mitchell Waldrop,et al.  Online learning: Campus 2.0 , 2013, Nature.

[16]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[17]  Qian Zhang,et al.  Modeling and Predicting Learning Behavior in MOOCs , 2016, WSDM.

[18]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[19]  Sarah Kellogg,et al.  Online learning: How to make a MOOC , 2013, Nature.

[20]  John G. Breslin,et al.  Analyzing MOOC Entries of Professionals on LinkedIn for User Modeling and Personalized MOOC Recommendations , 2016, UMAP.

[21]  Lubos Popelínský,et al.  Predicting drop-out from social behaviour of students , 2012, EDM.

[22]  David E. Pritchard,et al.  Studying Learning in the Worldwide Classroom Research into edX's First MOOC. , 2013 .

[23]  Justin Reich,et al.  Rebooting MOOC Research , 2015, Science.

[24]  Cathy Sandeen.  Integrating MOOCS into Traditional Higher Education: The Emerging “MOOC 3.0” Era , 2013 .

[25]  Lise Getoor,et al.  Learning Latent Engagement Patterns of Students in Online Courses , 2014, AAAI.

[26]  Jure Leskovec,et al.  Engaging with massive online courses , 2014, WWW.