Dr. Hans Marien

Martinus J. Langeveldgebouw
Heidelberglaan 1
Kamer G1.04
3584 CS Utrecht
Projecten
Project
Opsporen en voorkomen van laaggeletterdheid onder 12-15-jarigen in Nederland 01-09-2022 tot 01-09-2025
Algemene projectbeschrijving

With Henk Aarts and Hans Marien (both Social and Behavioural Sciences), and Mehdi Dastani and Marijn Schraagen (Information and Computing Sciences); the aim of this project is to design and develop AI tools for detecting and preventing low literacy in Dutch children, and for providing adequate and personalized support for improving literacy (with the Foundation for Open Speech Technology, Fontys University of Applied Sciences, Royal Library, Stichting Lezen, and other potential partners.

Rol
Uitvoerder
Financiering
Anders AI Lab and matching of Royal Library and Fontys Hogeschool

AI-approach to low-literacy

In the Netherlands, high levels of low-literacy tremendously challenge the functioning of society as it creates divides and profound inequalities. Approximately 2,5 million people are functionally illiterate, and their number is rising. Problems with reading and writing skills are related to school success, socio-economic status, health, and psychological well-being. Within the context of the Dutch Digitalization Strategy it is important to innovate and optimize public service to all citizens, but the problem of low-literacy is scarcely covered. The Netherlands benefits from human-centered AI systems to improve people’s quality of life, and keep them healthy and more resilient for as long as possible. Still, efforts to make these systems accessible and empower illiterate populations are yet to be seen. So it's important to cover the full spectrum of the low-literacy issue:

Detection: To signal low-literacy we use AI systems (e.g., Natural Language Processing, Speech technology) to improve detection of low-literacy among children and adults.

Intervention: How can AI systems be deployed to guide low-literate people to the right intervention programs? Here, we use AI systems to advice people in various age groups appropriately while matching the specific needs of a person without stigmatizing and restricting personal autonomy.

Assistance: Not all low-literate people can improve their reading and/or writing skill level through intervention and will benefit more from appropriate assistance. How could social robotics be utilized for providing assistance? Can robots learn to cover the social-emotional aspect of this human-robot interaction?