Custom Validation Procedure for Tesys Recommender System

Designing, implementing and validating a recommender system represents a challenge that has been tackled within many e- Learning platforms. Still, each proposed approach has to take into consideration the particular underlying data workflow and wrap-up together appropriate mechanisms (i.e., memory based, model-based or hybrid) to obtain an effective recommender system. This paper presents a custom-designed validation procedure for a recommender system that has been previously developed and integrated into Tesys e-Learning platform. The recommender system is evaluated in terms of correctly recommending concepts of study, in accordance with the learner's particular knowledge level measured by previously taken tests and the knowledge of all other learners that have answered quizzes in the same learning context. Experimental results show an increase of the percent of correctly recommended concepts over time. Within the validation mechanism, a comparative analysis with two test scenarios shows that proposed recommender has an increase in value for the percentage of correctly recommended concepts. The custom proposed evaluation procedure may quickly evaluate further improvements of the recommender system.

[1]  Erik Duval,et al.  Context-Aware Recommender Systems for Learning: A Survey and Future Challenges , 2012, IEEE Transactions on Learning Technologies.

[2]  Marian Cristian Mihaescu,et al.  TESYS: e-Learning Application Built on a Web Platform , 2006, ICE-B.

[3]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[4]  George Lekakos,et al.  Improving the prediction accuracy of recommendation algorithms: Approaches anchored on human factors , 2006, Interact. Comput..

[5]  Bradley N. Miller,et al.  Social Information Filtering : Algorithms for Automating “ Word of Mouth , ” , 2017 .

[6]  Xia Ning,et al.  Enhance E-Learning through Data Mining for Personalized Intervention , 2018, CSEDU.

[7]  Jonathan L. Herlocker,et al.  A collaborative filtering algorithm and evaluation metric that accurately model the user experience , 2004, SIGIR '04.

[8]  Rashmi R. Sinha,et al.  The role of transparency in recommender systems , 2002, CHI Extended Abstracts.

[9]  Denis Gillet,et al.  The 3A Personalized, Contextual and Relation-based Recommender System , 2010, J. Univers. Comput. Sci..

[10]  R. Kohli,et al.  Internet Recommendation Systems , 2000 .

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

[12]  Wayne Lee.  EXperimental design and analysis , 1975 .

[13]  C.M. Mihăescu,et al.  Learning analytics solution for building personalized quiz sessions , 2017, 2017 18th International Carpathian Control Conference (ICCC).

[14]  Kenneth Y. Goldberg,et al.  Eigentaste: A Constant Time Collaborative Filtering Algorithm , 2001, Information Retrieval.

[15]  Yiyu Yao.  Measuring retrieval effectiveness based on user preference of documents , 1995 .

[16]  John A. Swets,et al.  Effectiveness of information retrieval methods , 1969 .

[17]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.

[18]  O. R. Zaïane,et al.  Recommender Systems For E-learning: TowardsNon-intrusive Web Mining , 2006 .

[19]  Antonio Hernando,et al.  Collaborative filtering adapted to recommender systems of e-learning , 2009, Knowl. Based Syst..

[20]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[21]  Richi Nayak,et al.  An Improvement to Collaborative Filtering for Recommender Systems , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

[22]  Marian Cristian Mihaescu,et al.  Taking e-Assessment Quizzes - A Case Study with an SVD Based Recommender System , 2018, IDEAL.

[23]  Rakesh K. Tekade,et al.  Experimental Design and Analysis of Variance , 2018 .

[24]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[25]  Michael J. Pazzani,et al.  Learning Collaborative Information Filters , 1998, ICML.

[26]  Xiaohua Sun,et al.  A comparison of several algorithms for collaborative filtering in startup stage , 2005, Proceedings. 2005 IEEE Networking, Sensing and Control, 2005..