Are MOOC Learning Analytics Results Trustworthy? With Fake Learners, They Might Not Be!
- 74 Downloads
The rich data that Massive Open Online Courses (MOOCs) platforms collect on the behavior of millions of users provide a unique opportunity to study human learning and to develop data-driven methods that can address the needs of individual learners. This type of research falls into the emerging field of learning analytics. However, learning analytics research tends to ignore the issue of the reliability of results that are based on MOOCs data, which is typically noisy and generated by a largely anonymous crowd of learners. This paper provides evidence that learning analytics in MOOCs can be significantly biased by users who abuse the anonymity and open-nature of MOOCs, for example by setting up multiple accounts, due to their amount and aberrant behavior. We identify these users, denoted fake learners, using dedicated algorithms. The methodology for measuring the bias caused by fake learners’ activity combines the ideas of Replication Research and Sensitivity Analysis. We replicate two highly-cited learning analytics studies with and without fake learners data, and compare the results. While in one study, the results were relatively stable against fake learners, in the other, removing the fake learners’ data significantly changed the results. These findings raise concerns regarding the reliability of learning analytics in MOOCs, and highlight the need to develop more robust, generalizable and verifiable research methods.
KeywordsLearning Analytics MOOCs Replication research Sensitivity analysis Fake learners
GA’s research is supported by the Israeli Ministry of Science and Technology under project no. 713257.
- Alexandron, G., Ruipérez-Valiente, J.A., Pritchard, D.E. (2015a). Evidence of MOOC students using multiple accounts to harvest correct answers. Learning with MOOCs II, 2015.Google Scholar
- Alexandron, G., Zhou, Q., Pritchard, D. (2015b). Discovering the pedagogical resources that assist students in answering questions correctly – a machine learning approach. In Proceedings of the 8th international conference on educational data mining (pp. 520–523).Google Scholar
- Alexandron, G., Ruipėrez-Valiente, J.A., Chen, Z., Muñoz-Merino, P.J., Pritchard, D.E. (2017). Copying@Scale using harvesting accounts for collecting correct answers in a MOOC. Communication Education, 108, 96–114.Google Scholar
- Alexandron, G., Ruipérez-Valiente, J.A., Lee, S., Pritchard, D.E. (2018). Evaluating the robustness of learning analytics results against fake learners. In Proceedings of the thirteenth European conference on technology enhanced learning: Springer.Google Scholar
- Alexandron, G., Ruipérez-Valiente, J.A., Pritchard, D.E. (2019). Towards a general purpose anomaly detection method to identify cheaters in massive open online courses. In Proceedings of the 12th international conference on educational data mining.Google Scholar
- Baker, R., Walonoski, J., Heffernan, N., Roll, I., Corbett, A., Koedinger, K. (2008). Why students engage in “gaming the system” behavior in interactive learning environments. Journal of Interactive Learning Research, 19(2), 162–182.Google Scholar
- Champaign, J., Colvin, K.F., Liu, A., Fredericks, C., Seaton, D., Pritchard, D.E. (2014). Correlating skill and improvement in 2 MOOCs with a student’s time on tasks. In Proceedings of the first ACM conference on Learning @ scale conference - L@S ’14, (March): 11–20.Google Scholar
- De Ayala, R. (2009). The theory and practice of item response theory. Methodology in the social sciences. Guilford Publications.Google Scholar
- Du, X., Duivesteijn, W., Klabbers, M., Pechenizkiy, M. (2018). Elba: exceptional learning behavior analysis. In Educational data mining (pp. 312–318).Google Scholar
- Gardner, J., Brooks, C., Andres, J.M.L., Baker, R. (2018). Morf: a framework for MOOC predictive modeling and replication at scale. arXiv:1801.05236.
- Goldhammer, F. (2015). Measuring ability, speed, or both? challenges, psychometric solutions, and what can be gained from experimental control. Measurement: Interdisciplinary Research and Perspectives, 13(3-4), 133–164.Google Scholar
- Kim, J., Guo, P.J., Cai, C.J., Li, S.-W.D., Gajos, K.Z., Miller, R.C. (2014a). Data-driven interaction techniques for improving navigation of educational videos. In Proceedings of the 27th annual ACM symposium on user interface software and technology - UIST’14 (pp. 563–572).Google Scholar
- Kim, J., Guo, P.J., Seaton, D.T., Mitros, P., Gajos, K.Z., Miller, R.C. (2014b). Understanding in-video dropouts and interaction peaks in online lecture videos.Google Scholar
- Koedinger, K.R., Mclaughlin, E.A., Kim, J., Jia, J.Z., Bier, N.L. (2015). Learning is not a spectator sport doing is better than watching for learning from a MOOC, pp. 111–120.Google Scholar
- Krause, J., Perer, A., Ng, K. (2016). Interacting with predictions: visual inspection of black-box machine learning models. In Proceedings of the 2016 CHI conference on human factors in computing systems (pp. 5686–5697): ACM.Google Scholar
- MacHardy, Z., & Pardos, Z.A. (2015). Toward the evaluation of educational videos using bayesian knowledge tracing and big data. In Proceedings of the second (2015) ACM conference on learning @ scale, L@S ’15 (pp. 347–350): ACM.Google Scholar
- MacKinnon, J.G. (2009). Bootstrap hypothesis testing, chapter 6, pp. 183–213. John Wiley & Sons, Ltd.Google Scholar
- Meyer, J.P., & Zhu, S. (2013). Fair and equitable measurement of student learning in moocs: an introduction to item response theory, scale linking, and score equating. Research & Practice in Assessment, 8, 26–39.Google Scholar
- O’Neil, C. (2017). Weapons of math destruction: how big data increases inequality and threatens democracy. Broadway Books.Google Scholar
- Open Science Collaboration. (2015). Estimating the reproducibility of psychological science. Science, 349(6251). ISSN 0036-8075.Google Scholar
- Pardo, A., Mirriahi, N., Martinez-Maldonado, R., Jovanovic, J., Dawson, S., Gašević, D. (2016). Generating actionable predictive models of academic performance. In Proceedings of the sixth international conference on learning analytics & knowledge (pp. 474–478): ACM.Google Scholar
- Pardos, Z.A., Tang, S., Davis, D., Le, C.V. (2017). Enabling real-time adaptivity in MOOCs with a personalized next-step recommendation framework. In Proceedings of the fourth (2017) ACM conference on learning @ scale - L@S ’17. ISBN 9781450344500. https://doi.org/10.1145/3051457.3051471.
- Perez, S., Massey-Allard, J., Butler, D., Ives, J., Bonn, D., Yee, N., Roll, I. (2017). Identifying productive inquiry in virtual labs using sequence mining. In André, E., Baker, R., Hu, X., Rodrigo, M.M.T., du Boulay, B. (Eds.) Artificial intelligence in education (pp. 287–298). Cham: Springer International Publishing.Google Scholar
- Qiu, J., Tang, J., Liu, T. X., Gong, J., Zhang, C., Zhang, Q., Xue, Y. (2016). Modeling and predicting learning behavior in moocs. In Proceedings of the ninth ACM international conference on web search and data mining (pp. 93–102): ACM.Google Scholar
- Romero, C., & Ventura, S. (2017). Educational data science in massive open online courses. Wiley interdisciplinary reviews: data mining and knowledge discovery, WIREs Data Mining Knowl Discov, 01. https://doi.org/10.1002/widm.1187.
- Rosen, Y., Rushkin, I., Ang, A., Federicks, C., Tingley, D., Blink, M.J. (2017). Designing adaptive assessments in MOOCs. In Proceedings of the fourth (2017) ACM conference on learning @ scale, L@S ’17. ISBN 978-1-4503-4450-0 (pp. 233–236).Google Scholar
- Ruipérez-Valiente, J.A., Alexandron, G., Chen, Z., Pritchard, D.E. (2016). Using multiple accounts for harvesting solutions in MOOCs. In Proceedings of the third (2016) ACM conference on learning @ scale - L@S ’16 (pp. 63–70).Google Scholar
- Ruipérez-Valiente, J.A., Joksimović, S., Kovanović, V., Gašević, D., Muñoz Merino, P.J., Delgado Kloos, C. (2017a). A data-driven method for the detection of close submitters in online learning environments. In Proceedings of the 26th international conference on world wide web companion (pp. 361–368).Google Scholar
- Ruipérez-Valiente, J.A., Muñoz-Merino, P.J., Alexandron, G., Pritchard, D.E. (2017b). Using machine learning to detect ‘multiple-account’ cheating and analyze the influence of student and problem features. IEEE Transactions on Learning Technologies, 14(8), 1–11.Google Scholar
- Seshia, S.A., & Sadigh, D. (2016). Towards verified artificial intelligence. CoRR, arXiv:1606.08514, .
- Silver, N. (2012). The signal and the noise: why so many predictions fail–but some don’t. Penguin.Google Scholar
- U.S. Department of Education, Office of Educational Technology. (2012). Enhancing teaching and learning through educational data mining and learning analytics: an issue brief.Google Scholar
- van der Zee, T., & Reich, J. (2018). Open education science. AERA Open, 4 (3), 2332858418787466.Google Scholar
- Yudelson, M., Fancsali, S., Ritter, S., Berman, S., Nixon, T., Joshi, A. (2014). Better data beats big data. In Educational data mining 2014.Google Scholar