Evaluation of reading performance of primary school children: Objective measurements vs. subjective ratings

Erika Godde, Gérard Bailly, David Escudero, Marie-Line Bosse, Estelle Gillet-Perret


We analyze here readings of the same reference text by 116 children. We show that several factors strongly impact subjective rating of fluency, notably number of correct words, repetitions, errors, syllables spelled per minute. We succeeded in predicting four subjective scores – rated between 1 and 4 by human raters – from such objective measurements with a rather high precision (R > .8 for 3 out of 4 scores). This open the way for automatic multidimensional assessment of reading fluency using calibrated texts.


 DOI: 10.21437/WOCCI.2017-4

Cite as: Godde, E., Bailly, G., Escudero, D., Bosse, M., Gillet-Perret, E. (2017) Evaluation of reading performance of primary school children: Objective measurements vs. subjective ratings. Proc. WOCCI 2017: 6th International Workshop on Child Computer Interaction, 23-27, DOI: 10.21437/WOCCI.2017-4.


@inproceedings{Godde2017,
  author={Erika Godde and Gérard Bailly and David Escudero and Marie-Line Bosse and Estelle Gillet-Perret},
  title={Evaluation of reading performance of primary school children: Objective measurements vs. subjective ratings},
  year=2017,
  booktitle={Proc. WOCCI 2017: 6th International Workshop on Child Computer Interaction},
  pages={23--27},
  doi={10.21437/WOCCI.2017-4},
  url={http://dx.doi.org/10.21437/WOCCI.2017-4}
}