Abstract
Traditional intelligent systems recommend a teaching sequence to individual students without monitoring their ongoing learning attitude. It causes frustrations for students to learn a new skill and move them away from their target learning goal. As a step to make the best teaching strategy, in this paper a Personalized Skill-Based Math Recommender (PSBMR) framework has been proposed to automatically recommend pedagogical instructions based on a student’s learning progress over time. The PSBMR utilizes an adversarial bandit in contrast to the classic multi-armed bandit (MAB) problem to estimate the student’s ability and recommend the task as per his skill level. However, this paper proposes an online learning approach to model a student concept learning profile and used the Exp3 algorithm for optimal task selection. To verify the framework, simulated students with different behavioral complexity have been modeled using the Q-matrix approach based on item response theory. The simulation study demonstrates the effectiveness of this framework to act fairly with different groups of students to acquire the necessary skills to learn basic mathematics.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Miliband, D.: Personalised Learning: Building a New Relationship with Schools, Speech to the North of England Education Conference, Belfast, January 2004
Yago, H., Clemente, J., Rodriguez, D.: Competence-based recommender systems: a systematic literature review. Behav. Inf. Technol. 37(10–11), 958–977 (2018)
Ricci, F., Rokach, L., Shapira, B.: Introduction to Recommender Systems Handbook. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds.) Recommender Systems Handbook. Springer, Boston (2011). https://doi.org/10.1007/978-0-387-85820-3_1
Zaphiris, P., Ioannou, A. (eds.): LCT 2015. LNCS, vol. 9192. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-20609-7
Slivkins, A.: Introduction to Multi-Armed Bandits, April 2019. arXiv:1904.07272v3
Clement, B., Roy, D., Oudeyer, P.-Y., Lopes, M.: Online optimization of teaching sequences with multi-armed bandits. In: 7th International Conference on Education Data Mining, London, UK (2014)
Serrano-Guerrero, J., Romero, F.P., Olivas, J.A.: Hiperion: a fuzzy approach for recommending educational activities based on the acquisition of competencies. Inf. Sci. (NY) 248, 114–129 (2013)
Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32(1), 48–77 (2003)
Wang, Y., Heffernan, N.: Extending knowledge tracing to allow partial credit: using continuous versus binary nodes. In: Lane, H.C., Yacef, K., Mostow, J., Pavlik, P. (eds.) AIED 2013. LNCS (LNAI), vol. 7926, pp. 181–188. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39112-5_19
Reckase, M.D.: Multidimensional Item Response Theory Models. Springer, New York (2009). https://doi.org/10.1007/978-0-387-89976-3
Rupp, A.A., Templin, J.L.: Unique characteristics of diagnostic classification models: a comprehensive review of the current state-of-the-art. Meas. Interdiscip. Res. Perspect. 6(4), 219–262 (2008)
Chen, Y., Li, X., Liu, J., Ying, Z.: Recommendation system for adaptive learning. Appl. Psychol. Meas. 42(1), 24–41 (2018)
Koedinger, K.R., Brunskill, E., Baker, R.S., Mclaughlin, E.A., Stamper, J.: New potentials for data-driven intelligent tutoring system development and optimization. AI Mag. 34(3), 27–41 (2013)
Leighton, J.P., Gierl, M.J., Hunka, S.M.: The attribute hierarchy method for cognitive assessment: a variation on Tatsuoka’s rule-space approach. J. Educ. Meas. 41(3), 205–237 (2004)
Nino-Mora, J.: Stochastic scheduling. In: Floudas, C.A., Pardalos, P.M. (Eds.) Encyclopedia of Optimization, pp. 3818–3824 (2009)
Burtini, G., Loeppky, J., Lawrence, R.: A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit. arXiv:1510.00757v4
Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a rigged casino: the adversarial multi-armed bandit problem. In: Proceedings of Annual Symposium Foundations of Computer Science, Milwaukee, WI, pp. 322–331 (1995)
Lattimore, T., Szepesvá, C.: Bandit Algorithms. Cambridge University Press, Cambridge (2018). Draft of 28th July, Revision 1016
Schapire, R.E., Freund, Y.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 119–139 (1997)
Mertz, Jr., J.: Using a simulated student for instructional design. In: Proceedings of the Seventh World Conference on Artificial Intelligence in Education (1995)
Beck, J.: Modeling the student with reinforcement learning. Paper presented at the 6th Annual Conference on User Modelling, Sardina, Italy (1997)
Meneghetti, D.D.R., Junior, P.TA.: Application and Simulation of Computerized Adaptive Tests Through the Package catsim (2017). arXiv:1707.03012v2
Acknowledgment
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A4A1023746, No. 2019R1F1A1060799).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Islam, M.Z., Mehmood, K., Kim, H.S. (2020). Reinforcement Learning Based Interactive Agent for Personalized Mathematical Skill Enhancement. In: Slamanig, D., Tsigaridas, E., Zafeirakopoulos, Z. (eds) Mathematical Aspects of Computer and Information Sciences. MACIS 2019. Lecture Notes in Computer Science(), vol 11989. Springer, Cham. https://doi.org/10.1007/978-3-030-43120-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-43120-4_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43119-8
Online ISBN: 978-3-030-43120-4
eBook Packages: Computer ScienceComputer Science (R0)