Automated analysis of pupils' self-explanations of a narrative text

Philippe Dessus (1) , Maryse Bianco (1) , Aurélie Nardy (1) , Françoise Toffa (1) , Mihai Dascalu (2, 1) , Stefan Trausan-Matu (2)

1 LSE - Laboratoire des Sciences de l'Éducation (Grenoble)
2 Computer Science Department [Bucarest]

We present a method devised to automatically analyze pupils' verbalizations during reading and to reveal some of the strategies they use. An experiment with 44 primary school pupils (3rd and 5th grade) reading a narrative text and verbalizing what they understood at predefined breaks showed, firstly, that machine results are correlated with experts'; secondly, that the recall of recent sentences is not uniform across verbalizations and subject to a grade effect; thirdly, that there is a grade effect in the recall of distal causal sentences.

Domaines: Education

Philippe Dessus, Maryse Bianco, Aurélie Nardy, Françoise Toffa, Mihai Dascalu, et al.. Automated analysis of pupils' self-explanations of a narrative text. Meeting of the EARLI SIG 2 "Comprehension of Text and Graphics", Aug 2012, France. pp.52-54. ⟨hal-00906940⟩