Heterogeneous Features Integration in Deep Knowledge Tracing

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)

Abstract

Knowledge tracing is a significant research topic in educational data mining. The goal is to automatically trace students’ knowledge states by analyzing their exercise performance. Recently proposed Deep Knowledge Tracing (DKT) model has shown a significant improvement to solve this task by applying deep recurrent neural networks to learn interaction between knowledge components and exercises. The input of the model is only the one-hot encoding to represent the exercise tags and it excludes all other heterogeneous features, which may degrade the performance. To further improve the model performance, researchers have analyzed the heterogeneous features and provided manual ways to select the features and discretize them appropriately. However, the feature engineering efforts are not feasible for data with a huge number of features. To tackle with them, we propose an automatic and intelligent approach to integrate the heterogeneous features into the DKT model. More specifically, we encode the predicted response and the true response into binary bits and combine them with the original one-hot encoding feature as the input to a Long Short Term Memory (LSTM) model, where the predicted response is learned via Classification And Regression Trees (CART) on the heterogeneous features. The predicted response plays the role of determining whether a student will answer the exercise correctly, which can relieve the effect of exceptional samples. Our empirical evaluation on two educational datasets verifies the effectiveness of our proposal.

Keywords

Recurrent neural networks Knowledge tracing Decision tree 

Notes

Acknowledgment

The work described in this paper was partially supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. UGC/IDS14/16).

References

  1. 1.
    Czerniewicz, L., Deacon, A., Glover, M., Walji, S.: MOOC - making and open educational practices. J. Comput. High. Educ. 29(1), 81–97 (2017)CrossRefGoogle Scholar
  2. 2.
    Khajah, M., Lindsey, R.V., Mozer, M.: How deep is knowledge tracing?. In: EDM (2016)Google Scholar
  3. 3.
    Labutov, I., Studer, C.: Calibrated self-assessment. In: EDM (2016)Google Scholar
  4. 4.
    Corbett, A.T., Anderson, J.R.: Knowledge tracing: modelling the acquisition of procedural knowledge. User Model. User Adapt. Interact. 4(4), 253–278 (1994)CrossRefGoogle Scholar
  5. 5.
    Agrawal, R.: Data-driven education: some opportunities and challenges. In: EDM, p. 2 (2016)Google Scholar
  6. 6.
    Sweeney, M., Lester, J., Rangwala, H., Johri, A.: Next-term student performance prediction: a recommender systems approach. In: EDM, p. 7 (2016)Google Scholar
  7. 7.
    Baker, R.S.J., Corbett, A.T., Aleven, V.: More accurate student modeling through contextual estimation of slip and guess probabilities in bayesian knowledge tracing. In: Woolf, B.P., Aïmeur, E., Nkambou, R., Lajoie, S. (eds.) ITS 2008. LNCS, vol. 5091, pp. 406–415. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-69132-7_44 CrossRefGoogle Scholar
  8. 8.
    Pardos, Z.A., Heffernan, N.T.: Modeling individualization in a bayesian networks implementation of knowledge tracing. In: De Bra, P., Kobsa, A., Chin, D. (eds.) UMAP 2010. LNCS, vol. 6075, pp. 255–266. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-13470-8_24 CrossRefGoogle Scholar
  9. 9.
    Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L.J., Sohl-Dickstein, J.: Deep knowledge tracing. In: NIPS, pp. 505–513 (2015)Google Scholar
  10. 10.
    Xiong, X., Zhao, S., Inwegen, E.V., Beck, J.: Going deeper with deep knowledge tracing. In: EDM, pp. 545–550 (2016)Google Scholar
  11. 11.
    Huang, Y., Guerra, J., Brusilovsky, P.: A data-driven framework of modeling skill combinations for deeper knowledge tracing. In: EDM, pp. 593–594 (2016)Google Scholar
  12. 12.
    Wang, L., Sy, A., Liu, L., Piech, C.: Deep knowledge tracing on programming exercises. In: Proceedings of the Fourth ACM Conference on Learning@ Scale, pp. 201–204. ACM (2017)Google Scholar
  13. 13.
    Zhang, J., Shi, X., King, I., Yeung, D.: Dynamic key-value memory networks for knowledge tracing. In: WWW, pp. 765–774 (2017)Google Scholar
  14. 14.
    Huang, Y., González-Brenes, J.P., Brusilovsky, P.: General features in knowledge tracing to model multiple subskills, temporal item response theory, and expert knowledge. In: EDM, pp. 84–91 (2014)Google Scholar
  15. 15.
    Zhang, L., Xiong, X., Zhao, S., Botelho, A., Heffernan, N.T.: Incorporating rich features into deep knowledge tracing. In: Proceedings of the Fourth ACM Conference on Learning @ Scale, L@S 2017, pp. 169–172. Cambridge, 20–21 April 2017Google Scholar
  16. 16.
    Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. CRC Press, Boca Raton (1984)MATHGoogle Scholar
  17. 17.
    Quinlan, J.R.: C4. 5: Programs for Machine Learning. Elsevier, San Francisco (2014)Google Scholar
  18. 18.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  19. 19.
    Hu, J., Yang, H., King, I., Lyu, M.R., So, A.M.C.: Kernelized online imbalanced learning with fixed budgets. In: AAAI. Austin Texss, USA (2015)Google Scholar
  20. 20.
    Hu, J., Yang, H., Lyu, M.R., King, I., So, A.M.C.: Online nonlinear AUC maximization for imbalanced data sets. In: IEEE Transactions on Neural Networks and Learning Systems (2017)Google Scholar
  21. 21.
    Yang, H., Lyu, M.R., King, I.: Efficient online learning for multi-task feature selection. ACM Trans. Knowl. Discov. Data 7(2), 1–27 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Computer Science and EngineeringThe Chinese University of Hong KongShatinHong Kong
  2. 2.Department of ComputingHang Seng Management CollegeShatinHong Kong

Personalised recommendations