Learning Management Systems (LMSs) such as Blackboard, Moodle and Canvas have been widely adopted by schools and universities all around the world although LMSs currently face two major problems: limited data capture prone by the limitation which SCORM presents (Gibson, 2013), and adaptability by the lack of incorporation of Artificial Intelligence (AI) and machine learning algorithms (Graf and List, 2005; Aleven, 2015).
This research will use xAPI to overcome the limitations of SCORM and track learners’ experience data as they interact with online courses hosted by a corporate learning environment. xAPI is an evolved version of SCORM capable of tracking all kinds of learners’ data online and offline (xAPI). The aims of this research are to apply machine learning and Artificial Intelligence algorithms in order to (i) improve course content by identifying problem points within a course, and comparing it to refined versions of the course (ii) suggest courses for the learners based on their performance/experience from previous courses, and (iii) to make predictions on the learning outcomes based on the data gathered.
Knowledge Tracing (KT) has become the “de-facto standard for inferring student knowledge from performance data” (González-Brenes et al., 2014) and an “efficient approach to model student skill acquisition” (Huang et al., 2016). KT makes it possible to: determine mastery of skills, pinpoint strong/weak topics, and determine forgetfulness. This information can be used by course authors to suggest/recommend courses based on performance, pinpoint areas within a course where most learners struggle, and create recap courses to preserve mastered knowledge. This research will focus on knowledge tracing under the two following approaches: Bayesian Knowledge Tracing (BKT) (Corbett and Anderson, 1994; Khajah 2016) and Deep Knowledge Tracing (DKT) (Piech et al., 2015).
BIBLIOGRAPHY
Aleven, V., Sewall, J., Popescu, O., Xhakaj, F., Chand, D., Baker, R., Wang, Y., Siemens, G., Rosé, C., Gasevic, D. (2015) The Beginning of a Beautiful Friendship? Intelligent Tutoring Systems and MOOCs, in: Conati, C., Heffernan, N., Mitrovic, A., Verdejo, M.F. (Eds.), Artificial Intelligence in Education. Springer International Publishing, Cham, pp. 525–528. https://doi.org/10.1007/978-3-319-19773-9_53
Corbett, A.T., Anderson, J.R., 1994. Knowledge tracing: Modeling the acquisition of procedural knowledge. User Model User-Adap Inter 4, 253–278. https://doi.org/10.1007/BF01099821
Graf, S., List, B., (2005) An evaluation of open source e-learning platforms stressing adaptation issues. IEEE, pp. 163–165. https://doi.org/10.1109/ICALT.2005.54
Gibson, M., 2013. Does SCORM prevent good education? [WWW Document]. URL http://markgibson.info/2013/07/does-scorm-prevent-good-education.html (accessed 3.20.18).
González-Brenes, J., Huang, Y., Brusilovsky, P., (2014) General Features in Knowledge Tracing: Applications to Multiple Subskills, Temporal Item Response Theory, and Expert Knowledge. Proceedings of the 7th International Conference on Educational Data Mining (EDM 2014) 8.
Huang, Y., Guerra-Hollstein, J.D., Brusilovsky, P., 2016. A Data-Driven Framework of Modeling Skill Combinations for Deeper Knowledge Tracing. Presented at the Proceedings of the 9th International Conference on Educational Data Mining, p. 2.
Khajah, M., Lindsey, R.V., Mozer, M.C., 2016. How deep is knowledge tracing? arXiv:1604.02416 [cs].
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., Sohl-Dickstein, J., 2015. Deep Knowledge Tracing. In Advances in Neural Information Processing Systems 9.
xAPI, n.d. Overview [WWW Document]. Experience API. URL https://xapi.com/overview/ (accessed 3.20.18).
