Are Automatically Identified Reading Strategies Reliable Predictors of Comprehension?

  • Mihai Dascalu
  • Philippe Dessus
  • Maryse Bianco
  • Stefan Trausan-Matu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8474)


In order to build coherent textual representations, readers use cognitive procedures and processes referred to as reading strategies; these specific procedures can be elicited through self-explanations in order to improve understanding. In addition, when faced with comprehension difficulties, learners can invoke regulation processes, also part of reading strategies, for facilitating the understanding of a text. Starting from these observations, several automated techniques have been developed in order to support learners in terms of efficiency and focus on the actual comprehension of the learning material. Our aim is to go one step further and determine how automatically identified reading strategies employed by pupils with age between 8 and 11 years can be related to their overall level of understanding. Multiple classifiers based on Support Vector Machines are built using the strategies’ identification heuristics in order to create an integrated model capable of predicting the learner’s comprehension level.


Self-Explanations Reading Strategies Comprehension Prediction Identification Heuristics Support Vector Machines 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Millis, K., Magliano, J.P.: Assessing comprehension processes during reading. In: Sabatini, J.P., Albro, E.R., O’Reilly, T. (eds.) Assessing Reading in the 21st Century, pp. 35–53. Rowman & Littlefield Publishing, Lanham (2012)Google Scholar
  2. 2.
    McNamara, D.S., Magliano, J.P.: Self-explanation and metacognition. In: Hacher, J.D., Dunlosky, J., Graesser, A.C. (eds.) Handbook of Metacognition in Education, pp. 60–81. Erlbaum, Mahwah (2009)Google Scholar
  3. 3.
    McNamara, D.S., Scott, J.L.: Training reading strategies. In: 21th Annual Meeting of the Cognitive Science Society (CogSci 1999), pp. 387–392. Erlbaum, Hillsdale (1999)Google Scholar
  4. 4.
    McNamara, D.S.: SERT: Self-Explanation Reading Training. Discourse Processes 38, 1–30 (2004)CrossRefGoogle Scholar
  5. 5.
    Nash-Ditzel, S.: Metacognitive Reading Strategies Can Improve Self-Regulation. Journal of College Reading and Learning 40(2), 45–63 (2010)Google Scholar
  6. 6.
    Nardy, A., Bianco, M., Toffa, F., Rémond, M., Dessus, P.: Contrôle et régulation de la compréhension: l’acquisition de stratégies de 8 à 11 ans. In: David, J., Royer, C. (eds.) L’apprentissage de la lecture, p. 16. Peter Lang, Bern-Paris (in press)Google Scholar
  7. 7.
    Dascalu, M., Dessus, P., Trausan-Matu, Ş., Bianco, M., Nardy, A.: ReaderBench, an Environment for Analyzing Text Complexity and Reading Strategies. In: Lane, H.C., Yacef, K., Mostow, J., Pavlik, P. (eds.) AIED 2013. LNCS (LNAI), vol. 7926, pp. 379–388. Springer, Heidelberg (2013)Google Scholar
  8. 8.
    Dascalu, M.: Analyzing Discourse and Text Complexity for Learning and Collaborating, Studies in Computational Intelligence, vol. 534. Springer, Switzerland (2014)CrossRefGoogle Scholar
  9. 9.
    Cortes, C., Vapnik, V.N.: Support-Vector Networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  10. 10.
    van Dijk, T.A., Kintsch, W.: Strategies of discourse comprehension. Academic Press, New York (1983)Google Scholar
  11. 11.
    Piech, C., Huang, J., Chen, Z., Do, C., Koller, D.: Tuned models of peer assessment in MOOCs. In: Int. Conf. Educational Data Mining (EDM 2013). International Educational Data Mining Society, Memphis (2013)Google Scholar
  12. 12.
    Goldin, I.M.: Acounting for peer reviewer bias with Bayesian models. In: The Proceedings of the Workshop on Intelligent Support for Learning Groups at the 11th Int. Conf. on Intelligent Tutoring Systems (ITS 2012), Chania, Grece (2012)Google Scholar
  13. 13.
    O’Reilly, T.P., Sinclair, G.P., McNamara, D.S.: iSTART: A Web-based Reading Strategy Intervention that Improves Students’ Science Comprehension. In: CELDA 2004, p. 8. IADIS Press, Lisbon (2004)Google Scholar
  14. 14.
    McNamara, D.S., Boonthum, C., Levinstein, I.B.: Evaluating self-explanations in iSTART: Comparing word-based and LSA algorithms. In: Landauer, T.K., et al. (eds.) Handbook of Latent Semantic Analysis, pp. 227–241. Erlbaum, Mahwah (2007)Google Scholar
  15. 15.
    Jackson, G.T., Guess, R.H., McNamara, D.S.: Assessing cognitively complex strategy use in an untrained domain. In: 31st Annual Meeting of the Cognitive Science Society (CogSci 2009), pp. 2164–2169. Cognitive Science Society, Amsterdam (2009)Google Scholar
  16. 16.
    Miller, G.A.: WordNet: A Lexical Database for English. Communications of the ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  17. 17.
    Sagot, B.: WordNet Libre du Francais, WOLF (2008),
  18. 18.
    François, T., Miltsakaki, E.: Do NLP and machine learning improve traditional readability formulas? In: PITR2012, vol. 2012, pp. 49–57. ACL, Montreal (2012)Google Scholar
  19. 19.
    Bergstra, J., Bengio, Y.: Random Search for Hyper-Parameter Optimization. The Journal of Machine Learning Research 13, 281–305 (2012)zbMATHMathSciNetGoogle Scholar
  20. 20.
    Graesser, A.C., Singer, M., Trabasso, T.: Constructing inferences during narrative text comprehension. Psychological Review 101(3), 371–395 (1994)CrossRefGoogle Scholar
  21. 21.
    Graesser, A.C., McNamara, D.S., Kulikowich, J.: Coh-Metrix: Providing multilevel analyses of text characteristics. Educational Researcher 40(5), 223–234 (2011)CrossRefGoogle Scholar
  22. 22.
    Nelson, J., Perfetti, C., Liben, D., Liben, M.: Measures of text difficulty: Testing their predictive value for grade levels and student performance. Council of Chief State School Officers, Washington, DC (2012)Google Scholar
  23. 23.
    Todd, R.W., Khongput, S., Darasawang, P.: Coherence, cohesion and comments on students’ academic essays. Assessing Writing 12, 10–25 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Mihai Dascalu
    • 1
  • Philippe Dessus
    • 2
  • Maryse Bianco
    • 2
  • Stefan Trausan-Matu
    • 1
  1. 1.Computer Science DepartmentUniversity Politehnica of BucharestRomania
  2. 2.LSEUniv. Grenoble AlpesFrance

Personalised recommendations