Advertisement

Personalized Thread Recommendation for MOOC Discussion Forums

  • Andrew S. LanEmail author
  • Jonathan C. Spencer
  • Ziqi Chen
  • Christopher G. Brinton
  • Mung Chiang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11052)

Abstract

Social learning, i.e., students learning from each other through social interactions, has the potential to significantly scale up instruction in online education. In many cases, such as in massive open online courses (MOOCs), social learning is facilitated through discussion forums hosted by course providers. In this paper, we propose a probabilistic model for the process of learners posting on such forums, using point processes. Different from existing works, our method integrates topic modeling of the post text, timescale modeling of the decay in post excitation over time, and learner topic interest modeling into a single model, and infers this information from user data. Our method also varies the excitation levels induced by posts according to the thread structure, to reflect typical notification settings in discussion forums. We experimentally validate the proposed model on three real-world MOOC datasets, with the largest one containing up to 6,000 learners making 40,000 posts in 5,000 threads. Results show that our model excels at thread recommendation, achieving significant improvement over a number of baselines, thus showing promise of being able to direct learners to threads that they are interested in more efficiently. Moreover, we demonstrate analytics that our model parameters can provide, such as the timescales of different topic categories in a course.

Keywords

Discussion forums Hawkes process Personalized thread recommendation 

Supplementary material

478890_1_En_43_MOESM1_ESM.pdf (359 kb)
Supplementary material 1 (pdf 359 KB)

References

  1. 1.
    Blei, D., Ng, A., Jordan, M.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)zbMATHGoogle Scholar
  2. 2.
    Brinton, C.G., Buccapatnam, S., Wong, F., Chiang, M., Poor, H.V.: Social learning networks: efficiency optimization for MOOC forums. In: Proceedings of IEEE Conference on Computer Communications, pp. 1–9 (2016)Google Scholar
  3. 3.
    Brinton, C.G., Chiang, M., Jain, S., Lam, H., Liu, Z., Wong, F.: Learning about social learning in MOOCs: from statistical analysis to generative model. IEEE Trans. Learn. Technol. 7(4), 346–359 (2014)CrossRefGoogle Scholar
  4. 4.
    Brusilovsky, P., Somyürek, S., Guerra, J., Hosseini, R., Zadorozhny, V., Durlach, P.J.: Open social student modeling for personalized learning. IEEE Trans. Emerg. Topics Comput. 4(3), 450–461 (2016)CrossRefGoogle Scholar
  5. 5.
    Cong, G., Wang, L., Lin, C., Song, Y., Sun, Y.: Finding question-answer pairs from online forums. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 467–474, July 2008Google Scholar
  6. 6.
    Daley, D.J., Vere-Jones, D.: An Introduction to the Theory of Point Processes. Springer, New York (2003)zbMATHGoogle Scholar
  7. 7.
    Farajtabar, M., Yousefi, S., Tran, L., Song, L., Zha, H.: A continuous-time mutually-exciting point process framework for prioritizing events in social media. arXiv preprint arXiv:1511.04145, November 2015
  8. 8.
    Gillani, N., Eynon, R., Osborne, M., Hjorth, I., Roberts, S.: Communication communities in MOOCs. arXiv preprint arXiv:1403.4640, March 2014
  9. 9.
    Kardan, A., Narimani, A., Ataiefard, F.: A hybrid approach for thread recommendation in MOOC forums. Int. J. Soc. Behav. Educ. Econ. Bus. Indus. Eng. 11(10), 2195–2201 (2017)Google Scholar
  10. 10.
    Kim, M., Leskovec, J.: The network completion problem: Inferring missing nodes and edges in networks. In: Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 47–58, August 2011Google Scholar
  11. 11.
    Lan, A.S., Spencer, J.C., Chen, Z., Brinton, C.G., Chiang, M.: Personalized thread recommendation for MOOC discussion forums. arXiv preprint arXiv:1806.08468, June 2018
  12. 12.
    Lan, A.S., Studer, C., Baraniuk, R.G.: Time-varying learning and content analytics via sparse factor analysis. In: Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 452–461, August 2014Google Scholar
  13. 13.
    Lan, A.S., Studer, C., Waters, A.E., Baraniuk, R.G.: Joint topic modeling and factor analysis of textual information and graded response data. In: Proceedings of 6th International Conference on Educational Data Mining, pp. 324–325, July 2013Google Scholar
  14. 14.
    Linderman, S., Adams, R.: Discovering latent network structure in point process data. In: International Conference on Machine Learning, pp. 1413–1421, June 2014Google Scholar
  15. 15.
    Luo, D., et al.: Multi-task multi-dimensional Hawkes processes for modeling event sequences. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 3685–3691, August 2015Google Scholar
  16. 16.
    Mi, F., Faltings, B.: Adaptive sequential recommendation for discussion forums on MOOCs using context trees. In: Proceedings of International Conference on Educational Data Mining, pp. 24–31, June 2017Google Scholar
  17. 17.
    Miller, K., Jordan, M.I., Griffiths, T.L.: Nonparametric latent feature models for link prediction. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1276–1284, December 2009Google Scholar
  18. 18.
    Mozer, M., Lindsey, R.: Neural Hawkes process memories. In: NIPS Symposium: Recurrent Neural Networks, December 2016Google Scholar
  19. 19.
    Ramesh, A., Goldwasser, D., Huang, B., Daumé III, H., Getoor, L.: Understanding MOOC discussion forums using seeded LDA. In: Proceedings of Conference Association for Computational Linguistics, pp. 28–33, June 2014Google Scholar
  20. 20.
    Ramesh, A., Kumar, S., Foulds, J., Getoor, L.: Weakly supervised models of aspect-sentiment for online course discussion forums. In: Proceedings of Conference Association for Computational Linguistics, pp. 74–83, July 2015Google Scholar
  21. 21.
    Ritter, A., Cherry, C., Dolan, B.: Unsupervised modeling of Twitter conversations. In: Proceedings of Language Technologies, pp. 172–180, July 2010Google Scholar
  22. 22.
    Shi, X., Zhu, J., Cai, R., Zhang, L.: User grouping behavior in online forums. In: Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 777–786, June 2009Google Scholar
  23. 23.
    Simma, A., Jordan, M.I.: Modeling events with cascades of Poisson processes. In: Proceedings of Conference on Uncertainty in Artificial Intelligence, pp. 546–555, July 2010Google Scholar
  24. 24.
    Tomkins, S., Ramesh, A., Getoor, L.: Predicting post-test performance from online student behavior: a high school MOOC case study. In: Proceedings of International Conference on Educational Data Mining, pp. 239–246, June 2016Google Scholar
  25. 25.
    Wang, H., Wang, C., Zhai, C., Han, J.: Learning online discussion structures by conditional random fields. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 435–444, July 2011Google Scholar
  26. 26.
    Wang, X., Yang, D., Wen, M., Koedinger, K., Rosé, C.: Investigating how student’s cognitive behavior in MOOC discussion forums affect learning gains. In: Proceedings of International Conference on Educational Data Mining, pp. 226–233, June 2015Google Scholar
  27. 27.
    Wu, H., et al.: Modeling dynamic multi-topic discussions in online forums. In: Proceedings of Conference on American Association for Artificial Intelligence, pp. 1455–1460, July 2010Google Scholar
  28. 28.
    Yang, D., Piergallini, M., Howley, I., Rose, C.: Forum thread recommendation for massive open online courses. In: Proceedings of International Conference on Educational Data Mining, pp. 257–260, July 2014Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Andrew S. Lan
    • 1
    Email author
  • Jonathan C. Spencer
    • 1
  • Ziqi Chen
    • 2
  • Christopher G. Brinton
    • 1
    • 3
  • Mung Chiang
    • 4
  1. 1.Princeton UniversityPrincetonUSA
  2. 2.HKUSTClear Water BayHong Kong
  3. 3.Zoomi Inc.WayneUSA
  4. 4.Purdue UniversityWest LafayetteUSA

Personalised recommendations