Evaluating Simplicial Mixtures of Markov Chains for Modeling Student Metacognitive Strategies

  • April GalyardtEmail author
  • Ilya Goldin
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 89)


Modeling and discovery of the strategies that students use, both cognitive and metacognitive, is important for building accurate models of student knowledge and learning. We present a simulation study to examine whether simplicial mixtures of Markov chains (SM-MC) can be used to model student metacognitive strategies. We find that SM-MC models cannot be estimated on the moderately sized data sets common in education, and must be adapted to be useful for strategy modeling.


Transition Matrice Markov Chain Model Intelligent Tutoring System Metacognitive Strategy Cognitive Tutor 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This research has been supported in part by a postdoctoral award from the US Department of Education, Office of Education, Institute of Education Sciences to Ilya Goldin, award #R305B110003.


  1. Aleven V, Mclaren B, Roll I, Koedinger K (2006) Toward meta-cognitive tutoring: a model of help seeking with a cognitive tutor. Int J Artif Intell Educ 16:101–128Google Scholar
  2. Blei D, Lafferty J (2009) Topic models. In: Srivastava A, Sahami M (eds) Text mining: classification, clustering, and applications. Data mining and knowledge discovery series. Chapman & Hall/CRC, Boca RatonGoogle Scholar
  3. Erosheva E, Fienberg SE, Lafferty J (2004) Mixed-membership models of scientific publications. Proc Natl Acad Sci 101(Suppl 1):5220–5227CrossRefGoogle Scholar
  4. Galyardt A (2012) Mixed membership distributions with applications to modeling multiple strategy usage. Ph.D. thesis, Carnegie Mellon University.
  5. Galyardt A (2014) Interpreting mixed membership models: Implications of Erosheva’s representation theorem. In: Airoldi EM, Blei D, Erosheva E, Fienberg SE (eds) Handbook of mixed membership models. Chapman and Hall, Boca RatonGoogle Scholar
  6. Girolami M, Kaban A (2005) Sequential activity profiling: latent dirichlet allocation of markov chains. Data Min Knowl Discov 10:175–196CrossRefMathSciNetGoogle Scholar
  7. Goldin IM, Carlson R (2013) Learner differences and hint content. In: Proceedings of 16th international conference on artificial intelligence in education, Memphis, 2013Google Scholar
  8. Goldin IM, Koedinger KR, Aleven VAWMM (2012) Learner differences in hint processing. In: Yacef K, Zaïane O, Hershkovitz A, Yudelson M, Stamper J (eds) Proceedings of 5th international conference on educational data mining, Chania, 2012, pp 73–80Google Scholar
  9. Goldin IM, Koedinger KR, Aleven VAWMM Hints: You can’t have just one. In: D’Mello SK, Calvo RA, Olney A (eds) Proceedings of 6th international conference on educational data mining, 2013Google Scholar
  10. Mislevy RJ, Behrens JT, DiCerbo KE, Levy R (2012) Design and discovery in educational assessment: evidence-centered design, psychometrics, and educational data mining. J Educ Data Min 4(1):11–48Google Scholar
  11. VanLehn K (2008) Intelligent tutoring systems for continuous, embedded assessment. In: Dwyer C (ed) The future of assessment: shaping teaching and learning, Erbaum, pp 113–138Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.University of GeorgiaAthensUSA
  2. 2.Center for Digital DataAnalytics & Adaptive LearningPearsonUSA

Personalised recommendations