ABSTRACT
The focus of the learning analytics community bridges the gap between controlled educational research and data mining. Online learning platforms can be used to conduct randomized controlled trials to assist in the development of interventions that increase learning gains; datasets from such research can act as a treasure trove for inquisitive data miners. The present work employs a data mining approach on randomized controlled trial data from ASSISTments, a popular online learning platform, to assess the benefits of incorporating additional student performance data when attempting to differentiate between two user groups. Through a resampling technique, we show that partial credit, defined as an algorithmic combination of binary correctness, hint usage, and attempt count, can benefit assessment and group differentiation. Partial credit reduces sample sizes required to reliably differentiate between groups that are known to differ by 58%, and reduces sample sizes required to reliably differentiate between less distinct groups by 9%.
- Attali, Y. & Powers, D. (2010). Immediate feedback and opportunity to revise answers to open-end questions. Educational and Psychological Measures, 70 (1), 22--35.Google ScholarCross Ref
- Corbett, A. T., Anderson, J. R. (1995). Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge. User Modeling and User-Adapted Interaction, 4, 253--278.Google ScholarCross Ref
- Heffernan, N. & Heffernan, C. (2014). The ASSISTments Ecosystem: Building a Platform that Brings Scientists and Teachers Together for Minimally Invasive Research on Human Learning and Teaching. Int J of AIED, 24(4), 470--497.Google Scholar
- Koedinger, K. R. & Corbett, A. T. (2006). Cognitive tutors: Technology bringing learning science to the classroom. In K. Sawyer (Ed.), The Cambridge handbook of the learning sciences (61-78). New York: Cambridge University Press.Google Scholar
- MATLAB version R. 2013. a (2013). Natick, Massachusetts: MathWorks, Inc. Accessible at www.mathworks.comGoogle Scholar
- Ostrow, K., Donnelly, C., & Heffernan, N. (2015). Optimizing Partial Credit Algorithms to Predict Student Performance. In Santos, et al. (eds.) Proc of the 8th Int Conf on EDM, 404--407.Google Scholar
- Ostrow, K., Donnelly, C., Adjei, S., & Heffernan, N. (2015). Improving Student Modeling Through Partial Credit and Problem Difficulty. In Russell, D. M., Woolf, B., & Kiczales, G. (eds.) Proc of the 2nd ACM Conf on L@S, 11--20. Google ScholarDigital Library
- Ostrow, K., Heffernan, N., Heffernan, C., Peterson, Z. (2015). Blocking vs. Interleaving: Examining Single-Session Effects within Middle School Math Homework. In Conati, Heffernan, Mitrovic, & Verdejo (eds.) Proc of the 17th Int Conf on AIED. Springer International, 388--347.Google ScholarCross Ref
- Pardos, Z. A. & Heffernan, N. T. (2010). Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing. In De Bra, Kobsa, & Chin (eds.) Proc of the 18th Int Conf on UMAP, 255--266. Google ScholarDigital Library
- Pardos, Z. A., & Heffernan, N. T. (2011). KT-IDEM: Introducing Item Difficulty to the Knowledge Tracing Model. In Joseph A. Konstan et al. (Eds.), Proc of the 19th Int Conf on UMAP, 243--254. Google ScholarDigital Library
- Wang, Y. (2015). Data and Code for Enhancing the Efficiency and Reliability of Group Differentiation through Partial Credit: http://tiny.cc/LAK2016-ResamplingGoogle Scholar
- Wang, Y. & Heffernan, N. T. (2011). The "Assistance" Model: Leveraging How Many Hints and Attempts a Student Needs. In Proc of the 24th Int FLAIRS Conf.Google Scholar
- Wang, Y. & Heffernan, N. (2013). Extending Knowledge Tracing to Allow Partial Credit: Using Continuous versus Binary Nodes. In K. Yacef et al. (Eds.) AIED 2013, LNAI 7926, 181--188.Google Scholar
Index Terms
- Enhancing the efficiency and reliability of group differentiation through partial credit
Recommendations
Data mining for credit card fraud: A comparative study
Credit card fraud is a serious and growing problem. While predictive models for credit card fraud detection are in active use in practice, reported studies on the use of data mining approaches for credit card fraud detection are relatively few, possibly ...
Data mining application for cyber credit-card fraud detection system
ICDM'13: Proceedings of the 13th international conference on Advances in Data Mining: applications and theoretical aspectsSince the evolution of the internet, many small and large companies have moved their businesses to the internet to provide services to customers worldwide. Cyber credit card fraud or no card present fraud is increasingly rampant in the recent years for ...
Experimenting Choices of Video and Text Feedback in Authentic Foreign Language Assignments at Scale
L@S '17: Proceedings of the Fourth (2017) ACM Conference on Learning @ ScaleWith the development of "flipped classroom" concept and increasing usage of web-based learning platforms in foreign language teaching field, the effectiveness of online instant feedback come into researchers' focus, and whether or not teachers should ...
Comments