Identifying Key Learner on Online E-Learning Platform: An Effective Resistance Distance Approach

Teachers are never the only teacher in the class, especially in online e-learning environment. The key learner who is supposed to be more active and eager to spread knowledge and motivation to other classmates has a huge potentiality to improve the quality of teaching. However, the identification of such key learner is challenging which needs lots of human experience, especially when the contact channels between teachers and students are much more monotonous in online e-learning environment. Inspired by resistance distance theory, in this paper, we apply resistance distance and centrality into an interactive network of learners to identify key learner who can effectively motivate the whole class with discussion in e-learning platform. First, we define the terms of interactive network of learners with the node, edge, and graph. Then the distance between nodes is replaced with effective resistance distance to gain better understanding of propagation among the learners. Afterward, Closeness Centrality is utilized to measure the centrality of each learner in interactive network of learners. Experimental results show that the centrality we use can cover and depict the learners’ discussion activities well, and the key learner identified by our approach under apposite stimuli can effectively motivate the whole class’ learning performance.

[1]  Christian Bauckhage,et al.  Modeling Collaborative Similarity with the Signed Resistance Distance Kernel , 2008, ECAI.

[2]  Danah Boyd,et al.  Tweet, Tweet, Retweet: Conversational Aspects of Retweeting on Twitter , 2010, 2010 43rd Hawaii International Conference on System Sciences.

[3]  Eleni Stroulia,et al.  Measuring User Influence in Github: The Million Follower Fallacy , 2016, 2016 IEEE/ACM 3rd International Workshop on CrowdSourcing in Software Engineering (CSI-SE).

[4]  Enrico Bozzo,et al.  Resistance distance, closeness, and betweenness , 2013, Soc. Networks.

[5]  L. Freeman Centrality in social networks conceptual clarification , 1978 .

[6]  Qi He,et al.  TwitterRank: finding topic-sensitive influential twitterers , 2010, WSDM '10.

[7]  Scott Counts,et al.  Identifying topical authorities in microblogs , 2011, WSDM '11.

[8]  Tsai-Hsin Chu,et al.  With Good We Become Good: Understanding e-learning adoption by theory of planned behavior and group influences , 2016, Comput. Educ..

[9]  Philip S. Yu,et al.  A holistic lexicon-based approach to opinion mining , 2008, WSDM '08.

[11]  Zivadin Micic,et al.  A web-based intelligent report e-learning system using data mining techniques , 2013, Comput. Electr. Eng..

[12]  H. Clements,et al.  Blackwell Encyclopedia of Sociology , 2008 .

[13]  Ling Feng,et al.  Predicting lifespans of popular tweets in microblog , 2012, SIGIR '12.

[14]  Stephan Schmidt,et al.  Collaborative Filtering Using Electrical Resistance Network Models , 2007, ICDM.

[15]  Douglas J. Klein,et al.  Co-authorship, rational Erdős numbers, and resistance distances in graphs , 2004, Scientometrics.

[16]  Mervyn J. Wighting,et al.  A Comparative Analysis of Student Motivation in Traditional Classroom and E-Learning Courses , 2007 .

[17]  Prabhas Chongstitvatana,et al.  Indexing Simple Graphs by Means of the Resistance Distance , 2016, IEEE Access.

[18]  Marco Saerens,et al.  The Application of New Concepts of Dissimilarities between Nodes of a Graph to Collaborative Filtering , 2004 .

[19]  Milos Hauskrecht,et al.  Effective query expansion with the resistance distance based term similarity metric , 2010, SIGIR.

[20]  Hosung Park,et al.  What is Twitter, a social network or a news media? , 2010, WWW '10.