SeqSense: Video Recommendation Using Topic Sequence Mining

  • Chidansh Bhatt
  • Matthew CooperEmail author
  • Jian Zhao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10705)


This paper examines content-based recommendation in domains exhibiting sequential topical structure. An example is educational video, including Massive Open Online Courses (MOOCs) in which knowledge builds within and across courses. Conventional content-based or collaborative filtering recommendation methods do not exploit courses’ sequential nature. We describe a system for video recommendation that combines topic-based video representation with sequential pattern mining of inter-topic relationships. Unsupervised topic modeling provides a scalable and domain-independent representation. We mine inter-topic relationships from manually constructed syllabi that instructors provide to guide students through their courses. This approach also allows the inclusion of multi-video sequences among the recommendation results. Integrating the resulting sequential information with content-level similarity provides relevant as well as diversified recommendations. Quantitative evaluation indicates that the proposed system, SeqSense, recommends fewer redundant videos than baseline methods, and instead emphasizes results consistent with mined topic transitions.


Content-based video recommendation Educational video 


  1. 1.
    Onah, D.F., Sinclair, J., Boyatt, R.: Dropout rates of massive open online courses: behavioural patterns. In: EDULEARN 2014 Proceedings, pp. 5825–5834 (2014)Google Scholar
  2. 2.
    UIL Policy Brief: Making large-scale literacy campaigns and programmes work (2016)Google Scholar
  3. 3.
    Cope, B., Kalantzis, M.: e-Learning Ecologies: Principles for New Learning and Assessment. Routledge, Abingdon (2017)Google Scholar
  4. 4.
    Levin, R.: Announcing Coursera for Business (2016). Accessed 19 July 2017
  5. 5.
    Zheng, S., Rosson, M.B., Shih, P.C., Carroll, J.M.: Understanding student motivation, behaviors and perceptions in MOOCs. In: Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing. CSCW 2015, New York, NY, USA, pp. 1882–1895. ACM (2015)Google Scholar
  6. 6.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993–1022 (2003)zbMATHGoogle Scholar
  7. 7.
    Zhu, Q., Shyu, M.L., Wang, H.: Videotopic: content-based video recommendation using a topic model. In: ISM, pp. 219–222. IEEE Computer Society (2013)Google Scholar
  8. 8.
    Wang, Y., Agichtein, E., Benzi, M.: TM-LDA: efficient online modeling of latent topic transitions in social media. In: KDD, pp. 123–131. ACM (2012)Google Scholar
  9. 9.
    AlSumait, L., Barbará, D., Domeniconi, C.: On-line LDA: adaptive topic models for mining text streams with applications to topic detection and tracking. In: ICDM, pp. 3–12. IEEE (2008)Google Scholar
  10. 10.
    Ramesh, A., et al.: Understanding MOOC discussion forums using seeded LDA. In: Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications (2014)Google Scholar
  11. 11.
    Adcock, J., Cooper, M., Denoue, L., Pirsiavash, H., Rowe, L.A.: TalkMiner: a lecture webcast search engine. In: ACM Multimedia, pp. 241–250. ACM (2010)Google Scholar
  12. 12.
    Kinnebrew, J.S., Loretz, K.M., Biswas, G.: A contextualized, differential sequence mining method to derive students’ learning behavior patterns. J. Educ. Data Min. 5(1), 190–219 (2013)Google Scholar
  13. 13.
    Agrawal, R., Christoforaki, M., Gollapudi, S., Kannan, A., Kenthapadi, K., Swaminathan, A.: Mining videos from the web for electronic textbooks. In: Glodeanu, C.V., Kaytoue, M., Sacarea, C. (eds.) ICFCA 2014. LNCS, vol. 8478, pp. 219–234. Springer, Cham (2014). Google Scholar
  14. 14.
    Doroudi, S., Holstein, K., Aleven, V., Brunskill, E.: Sequence matters, but how exactly? A method for evaluating activity sequences from data. In: International Conference on Educational Data Mining EDM (2016)Google Scholar
  15. 15.
    Morales, C.R., Pérez, A.P., Soto, S.V., Martınez, C.H., Zafra, A.: Using sequential pattern mining for links recommendation in adaptive hypermedia educational systems. Curr. Dev. Technol.-Assist. Educ. 2, 1016–1020 (2006)Google Scholar
  16. 16.
    Pardos, Z.A., Tang, S., Davis, D., Le, C.V.: Enabling real-time adaptivity in MOOCs with a personalized next-step recommendation framework. In: ACM Conference on Learning @ Scale, pp. 23–32. ACM (2017)Google Scholar
  17. 17.
    Fournier-Viger, P., Faghihi, U., Nkambou, R., Nguifo, E.M.: CMRules: mining sequential rules common to several sequences. Knowl.-Based Syst. 25, 63–76 (2012)CrossRefGoogle Scholar
  18. 18.
    Fournier-Viger, P., Gomariz, A., Gueniche, T., Mwamikazi, E., Thomas, R.: TKS: efficient mining of top-k sequential patterns. In: Motoda, H., Wu, Z., Cao, L., Zaiane, O., Yao, M., Wang, W. (eds.) ADMA 2013. LNCS, vol. 8346, pp. 109–120. Springer, Heidelberg (2013). CrossRefGoogle Scholar
  19. 19.
    Fournier-Viger, P., Tseng, V.S.: TNS: mining top-k non-redundant sequential rules. In: SAC, pp. 164–166. ACM (2013)Google Scholar
  20. 20.
    Guille, A., Soriano-Morales, E.-P.: TOM: a library for topic modeling and browsing. In: Conférence sur l’Extraction et la Gestion des Connaissances, Reims, France, January 2016. Actes de la 16ème Conférence sur l’Extraction et la Gestion des Connaissances (2016).
  21. 21.
    Sievert, C., Shirley, K.E.: LDAvis: a method for visualizing and interpreting topics. In: Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces, pp. 63–70 (2014)Google Scholar
  22. 22.
    Fournier-Viger, P., Lin, J.C.W., Kiran, R.U., Koh, Y.S.: A survey of sequential pattern mining. Data Sci. Pattern Recogn. 1, 54–77 (2017)Google Scholar
  23. 23.
    Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)CrossRefzbMATHGoogle Scholar
  24. 24.
    Kruskal, J.B.: Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 29(1), 1–27 (1964)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Chuang, J., Manning, C.D., Heer, J.: “Without the clutter of unimportant words”: descriptive keyphrases for text visualization. ACM Trans. Comput.-Hum. Interact. 19(3), 19 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.FX Palo Alto LaboratoryPalo AltoUSA

Personalised recommendations