Abstract
This paper proposes a method for the identification of the “Leader Learners” within Massive Open Online Courses (MOOCs) in order to improve the support process. The “Leader Learners” are those who will be mobilized to animate the forum. Their role is to help the other learners find the information they need during the MOOC so as not to drop it. This method is based on the Dominance-based Rough Set Approach (DRSA) to infer a preference model generating a set of decision rules. The DRSA relies on the expertise of the human decision makers, who are in our case the pedagogical team, to make a multicriteria decision based on their preferences. This decision concerns the classification of learners either in the decision class Cl1 of the “Non Leader Learners” or in the decision class Cl2 of the “Leader Learners”. Our method is validated on a French MOOC proposed by a Business School in France.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barak, M.: The same mooc delivered in two languages: examining knowledge construction and motivation to learn. In: Proceedings of the EMOOCS, pp. 217–223 (2015)
Belton, V., Pictet, J.: A framework for group decision using a MCDA model: sharing, aggregation or comparing individual information. Revue des Systemes de Decision 6, 283–303 (1997)
Bolloju, N., Khalifa, M., Turban, E.: Integrating knowledge management into enterprise environments for the next generation decision support. Decis. Support Syst. 33, 163–176 (2002)
Boughzala, I., Briggs, R.O.: A value frequency model of knowledge sharing: an exploratory study on knowledge sharability in cross organizational collaboration. Electron. Mark. 22(1), 9–19 (2012)
Buckingham Shum, S., Ferguson, R.: Social learning analytics. Educ. Technol. Soc. 15(3), 3–26 (2012)
Caron, P.A., Heutte, J., Rosselle, M.: Rapport d’Expertise et Accompagnement par la recherche du dispositif expérimental MOOC iNum (2012)
Cohen, W., Levinthal, D.: Absorptive capacity: A new perspective on learning and innovation. Adm. Sci. Q. 35, 128–152 (1990)
Downes, S.: What Makes a MOOC Massive. Blog Post (2013)
Gooderham, P.: Enhancing knowledge transfer in multinational corporations: a dynamic capabilities driven model. Knowl. Manag. Res. Pract. 5(1), 34–43 (2007). doi:10.1057/palgrave.kmrp.8500119
Greco, S., Matarazzo, S., Slowinski, S.: Rough sets theory for multicriteria decision analysis. Eur. J. Oper. Res. 129, 1–47 (2001)
Kizilcec, R., Piech, C., Schneider, E.: Deconstructing disengagement: analyzing leaner subpopulations in massive open online courses. In: Third International Conference on Learning Analytics and Knowledge LAK 2013, pp. 170–179 (2013)
Morris, N., Hotchkiss, S., Swinnerton, B.: Can demographic information predict MOOC learner outcomes? In: Proceedings of the EMOOC Stakeholder Summit, pp. 199–207 (2015)
Pawlak, Z.: Rough sets. Int. J. Comput. Sci. 11(5), 341–356 (1982)
Rayyan, S., Seaton, D.T., Belcher, J., Pritchard, D.E., Chuang, I.: Participation and performance in 8.02x electricity and magnetism: the first physics MOOC from MITx. arXiv. In: Proceedings of the Physics Education Research Conference (2013)
Refaeilzadeh, P., Tang, L., Liu, H.: Cross-validation. In: Liu, L., Özsu, M.T. (eds.) Encyclopedia of Database Systems, pp. 532–538. Springer, Heidelberg (2009)
Suriel, R.L., Atwater, M.M.: From the contributions to the action approach: white teacher. J. Res. Sci. Teach. 49(10), 1271–1295 (2012)
Viberg, O., Messina Dahlberg, G.: MOOCs’ structure and knowledge management. In: Proceeding of the 21st International Conference on Computers in Education, Depansar Bali, Indonesia (2013)
Wolff, A., Zdrahal, Z., Herrmannov, D., Kuzilek, J., Hlosta, M.: Developing predictive models for early detection of at-risk students on distance learning modules. In: Workshop: Machine Learning and Learning Analytics at LAK, Indianapolis (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A List of the Constructed Criteria Family
A List of the Constructed Criteria Family
Criterion | Description | Scale | P |
|---|---|---|---|
g1: Study level | Indicates the actual study level of the learner or the last diploma he obtained | 1: Scholar student; 2: High school student; 3: PhD Student; 4: Doctor | ↑ |
g 2 : Level of technical skills | Indicates the extent to which the learner masters the use of the computer tools | 1: Basic; 2: Average; 3: Expert | ↑ |
g 3 : Level of proficiency in MOOC language | Indicates the extent to which the learner masters the language of the MOOC | 1: Basic; 2: Average; 3: Good | ↑ |
g 4 : Motivation for MOOC registration | Indicates the motivation behind the participation of the learner in the MOOC | 1: Just to discover the MOOCs; 2: To exchange ideas with the other learners or to have a certificate; 3: To exchange ideas with the other learners and to have a certificate | ↑ |
g 5 : Previous experience with MOOCs | Indicates whether the learner has a previous experience on learning via MOOCs or not | 0: No experience at all; 1: At least one experience | ↑ |
g 6 : Mastery level of the subject of the MOOC | Indicates to which extent the learner masters both the topic and the theme of the MOOC | 0: No knowledge at all; 1: Average knowledge; 2: Deepened knowledge | ↑ |
g 7 : Probability to finish the MOOC | Indicates the probability for a learner to carry-on the MOOC activities until the end | 1: Very weak; 2: Weak; 3: Average; 4: Strong; 5: Very strong | ↑ |
g 8 : Weekly availability predicted | Indicates the estimative weekly availability of the learner to follow the MOOC | 1: Less than one hour; 2: From one to two hours; 3: From two to three hours; 4: Four hours or more | ↑ |
g 9 : Number of add message | Indicates the number of the messages added on the forums per week | n \( \in \) n; n ≥ 0 is the maximum number of the added messages per week | ↑ |
g 10 : Number of responses published on the forum | Indicates the weekly number of the responses to an asked question published on the forum | m \( \in \) n; m ≥ 0 is the maximum number of answers per week | ↑ |
g 11 : Number of questions asked on the forum | Indicates the weekly number of questions asked by learners on the forum | k \( \in \) n; k ≥ 0 is the maximum weekly number of questions | ↑ |
g 12 : Frequency of navigation on the MOOC site | Indicates the capacity of the learner to interact with the site. It is calculated upon the number of resources consulted by week | p∈n such that p ≥ 0 is the weekly number of site consultation by the learner | ↑ |
g 13 : Score | Indicates the weekly score the learner got on the set of activities he made | The note \( \in \) [0, 10] | ↑ |
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Bouzayane, S., Saad, I. (2017). How to Help a Pedagogical Team of a MOOC Identify the “Leader Learners”?. In: Bajwa, D., Koeszegi, S., Vetschera, R. (eds) Group Decision and Negotiation. Theory, Empirical Evidence, and Application. GDN 2016. Lecture Notes in Business Information Processing, vol 274. Springer, Cham. https://doi.org/10.1007/978-3-319-52624-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-52624-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52623-2
Online ISBN: 978-3-319-52624-9
eBook Packages: Business and ManagementBusiness and Management (R0)