A better understanding of how children read and comprehend a short text, and what makes this process occasionally difficult, slow and inefficient is key to improving people’s education level, professional qualification and social cohesion. ReadLet uses portable ICT technology and cloud computing to collect, time-align, integrate and analyse large streams of multimodal reading data from early graders, captured with an affordable tablet frontend. The data are related to levels of reading complexity within the text, which are automatically annotated with NLP tools. While information technology cannot supplant the role and professional judgement of teachers and clinical specialists, by providing online databases of automatically classified cross-sectional and longitudinal data, accurate statistical modelling and computer simulations, ReadLet helps professionals to assess the level of reading skills reached by the child, and decide which intervention programmes and measures are most appropriate.
The ReadLet data involve finger tracking data, which give us a quite precise indication of where in the text the child is focusing on at each point in time, as well as audio recordings of the child reading the text. When text, finger tracking data and audio recordings are aligned, we end up with a fine-grained depiction of a child’s reading behaviour that looks like this:
Below you can watch a video with a demonstration of finger tracking and audio recording of a child reading a text using ReadLet: