ReadLet: an ICT platform for the assessment of reading efficiency in early graders

Reading is not just word decoding, but the joint product of decoding and deep linguisticcomprehension [ 1 , 2 ]. Effective linguistic comprehension relies on language skills such assemantic and syntactic awareness. Both decoding and linguistic comprehension are necessary forreading comprehension, and neither is by itself sufficient [ 2 ]. However, current protocols forreading assessment measure decoding (reading accuracy and speed) and reading comprehensionseparately [ 3 , 4 , 5 ]. This does not allow evaluation of reading efficiency [ 6 ], defined as the abilityto fully understand connected texts by minimising reading time, a cognitive ability that lies at theroots of students' academic achievement [ 8 , 7 ]. ReadLet is an ICT platform specifically designedto provide accurate, evidence-based assessment of reading efficiency in early grade children, byoffering an ecological, non-invasive protocol for extensive data elicitation, storage and analysis.With ReadLet, early graders at school can read a one or two page text displayed on atablet touchscreen, either silently or aloud. Children are asked to slide their finger across thewords as they read, to guide directional tracking. After reading, the child is prompted with a fewmultiple-answer questions on text content presented one at a time, while the text remainsdisplayed on the screen for the child to be able to retrieve relevant information. In the process,the tablet keeps track of time-aligned multimodal data: voice recording, finger sliding time, timeof reading, time of question answering, and number of correct answers. Data are recorded, storedlocally, sent to the ReadLet server through an internet connection, and processed remotely by abattery of cloud-based services, analysing data automatically to produce a detailed quantitativesignature of each reading session. A server-based database aggregates anonymised data to makethem available for specialists. Also individual's longitudinal profiles are stored, for them bequeried and inspected upon authorised access.The platform combines portable ICT technology and cloud computing with a number ofmodality-specific software modules, implemented as web services including: i) a text processingand readability assessment service, consisting in a battery of tools for automated linguisticannotation of written texts and a machine-learning component assigning a readability score toannotated texts [ 9 ]; ii) a finger touch processing service aligning the child's finger sliding withthe written text and measuring speed fluctuations; iii) a speech processing and decodingassessment service, aligning the acoustic record of child's reading with the written text andassessing correctness of recoding [ 10 ]. At the time of writing, the platform includes the first twomodules only. Preliminary testing of a prototype version of ReadLet technology with apopulation of about 200 pupils aged 8 to 11, both male and female, varying for socio-economicstatus, language (Italian, French and Arabic) and geographical area (Italy and Morocco), showedthat children are extremely responsive to using a tablet for reading, and very easy to engage inwhat they perceive as an enjoyable experience. We expect online databases of automaticallyclassified cross-sectional and longitudinal data, accurate statistical modelling and developmentaltrends of reading literacy to help education professionals and clinical specialists assess the levelof reading skills reached by the child, and decide which intervention programmes and measuresare most appropriate. While information technology cannot and should not supplant the role andprofessional judgement of teachers and therapists, the project intends to provide portable tools,models and data for timely screening and daily management of reading difficulties and disorders.