A Collaborative Learning Grouping Strategy with Early Warning Function Based on Complementarity Degree

  • Zhizhuang Li
  • Zhengzhou ZhuEmail author
  • Qiongyu Xie
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11841)


Organizing groups is a critical process in implementing cooperative learning. The grouping strategy based on the degree of complementarity is a popular grouping strategy at present. However, the existing collaborative learning grouping strategy based on the degree of complementarity has disadvantages such as insufficient modeling accuracy for students’ ability and lack of rationality for the reasons of regrouping. This paper proposes a collaborative learning grouping strategy with early warning function based on the degree of complementary mastery of knowledge points. First, we take knowledge points as the minimum unit, and use linear regression and expectation maximization algorithm to accurately model each student’s mastery of each knowledge point. Then we use the inverse clustering algorithm based on knowledge points to classify students. Finally, we use LSTM neural network to predict the scores of each group in the next week, and early warning was given to the groups with significantly reduced predicted scores, and targeted suggestions were put forward for them according to the types of the warned groups. Experimental results show that the grouping strategy proposed in this paper can effectively improve the learning effect of students. The average precision and average recall of LSTM based group early warning were 30.1% and 27.6% higher than that based on linear regression, respectively.


Cooperative learning Grouping strategy Learning early-warning Cognitive diagnosis LSTM EM algorithm Linear regression 



This paper was supported by National Key Research and Development Program of China (Grant No. 2017YFB1402400), Ministry of Education “Tiancheng Huizhi” Innovation Promotes Education Fund (Grant No. 2018B01004), National Natural Science Foundation of China (Grant No. 61402020, 61573356), and CERNET Innovation Project (Grant No. NGII20170501).


  1. 1.
    Webb, N.M., Troper, J.D., Fall, R.: Constructive activity and learning in collaborative small groups. J. Educ. Psychol. 87(3), 406–423 (1995)CrossRefGoogle Scholar
  2. 2.
    Jong, B., et al.: Effect of knowledge complementation grouping strategy for cooperative learning on online performance and learning achievement. Comput. Appl. Eng. Educ. 22(3), 541–550 (2014)CrossRefGoogle Scholar
  3. 3.
    Lai, C., et al.: The impact of peer interaction on group strategy in cooperative learning environment.–273.1213
  4. 4.
    Chan, T.Y., et al.: Applying learning achievement and thinking styles to cooperative learning grouping. In: Frontiers in Education Conference-Global Engineering: Knowledge Without Borders. IEEE (2007)Google Scholar
  5. 5.
    Wang, Y., Li, Y., Liao, H.: Using a genetic algorithm to determine optimal complementary learning clusters for ESL in Taiwan. Expert Syst. Appl. 38(12), 14832–14837 (2011)CrossRefGoogle Scholar
  6. 6.
    Wu, Y.: Using complementary grouping strategy for cooperative learning. Int. J. Intell. Inf. Database Syst. 8(1), 49–63 (2014)Google Scholar
  7. 7.
    Su, H.M., Shih, T.K., Chen, Y.H.: Grouping teammates based on complementary degree and social network analysis using genetic algorithm. In: International Conference on Ubi-Media Computing & Workshops. IEEE (2014)Google Scholar
  8. 8.
    Tien, H.-W., Lin, Y.-S., Chang, Y.-C., Chu, C.-P.: A genetic algorithm-based multiple characteristics grouping strategy for collaborative learning. In: Chiu, D.K.W., et al. (eds.) ICWL 2013. LNCS, vol. 8390, pp. 11–22. Springer, Heidelberg (2015). Scholar
  9. 9.
    Jong, B., Wu, Y., Chan, T.: Dynamic grouping strategies based on a conceptual graph for cooperative learning. IEEE Trans. Knowl. Data Eng. 18(6), 738–747 (2006)CrossRefGoogle Scholar
  10. 10.
    Macfadyen, L.P., Dawson, S.: Mining LMS data to develop an “early warning system” for educators: a proof of concept. Comput. Educ. 54(2), 1–599 (2010)CrossRefGoogle Scholar
  11. 11.
    He, W., Yen, C.J.: Using data mining for predicting relationships between online question theme and final grade. J. Educ. Technol. Soc. 15(3), 77–88 (2012)Google Scholar
  12. 12.
    Hu, Y.H., Lo, C.L., Shih, S.P.: Developing early warning systems to predict students’ online learning performance. Comput. Hum. Behav. 36, 469–478 (2014)CrossRefGoogle Scholar
  13. 13.
    Cheng, X., et al.: A novel learning early-warning model based on random forest algorithm. In: Nkambou, R., Azevedo, R., Vassileva, J. (eds.) ITS 2018. LNCS, vol. 10858, pp. 306–312. Springer, Cham (2018). Scholar
  14. 14.
    Liu, J., Yang, Z., Wang, X., Zhang, X., Feng, J.: An early-warning method on e-learning. In: Liu, S., Glowatz, M., Zappatore, M., Gao, H., Jia, B., Bucciero, A. (eds.) eLEOT 2018. LNICST, vol. 243, pp. 62–72. Springer, Cham (2018). Scholar
  15. 15.
    Sansone, D.: Beyond early warning indicators: high school dropout and machine learning. Oxford Bull. Econ. Stat. 81(2), 456–485 (2019)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Software and MicroelectronicsPeking UniversityBeijingChina
  2. 2.Anhui Normal UniversityWuhuChina

Personalised recommendations