Goodnight Moon, Hello Early Literacy Screening

Help educators provide effective early literacy intervention by scoring audio clips from literacy screeners. #education

$30,000 in prizes
Completed jan 2025
399 joined

About the project


Your work has the potential to bring about transformative changes in literacy screenings that take place in classrooms. Automating these processes can reduce the administrative burden on teachers, increase accuracy, and conserve educational resources. Advanced data-driven techniques also have the potential to diminish bias and errors in human scoring; and with consistent and unbiased linguistic assessments, early detection of learning difficulties in students and improved reading outcomes are possible.

Reach Every Reader

Reach Every Reader (RER) is a research initiative dedicated to tackling childhood literacy challenges. RER focuses on developing pre-literacy skills in early childhood, creating diagnostic tools for literacy assessment, supporting early intervention and readers' progress, providing educators with literacy resources, and collaborating with researchers and organizations to scale their solutions. RER has reached more than 58,000 children, 28,000 educators and 7,000 parent caregivers in 47 states. Learn more in the video below.

The RER literacy screening assessment

The data in this challenge come from the RER literacy screening assessment. The assessment battery includes 22 tasks that measure critical skills children develop in reading and language from kindergarten through 3rd grade. For each child, the assessment predicts the likelihood of being a proficient reader up to the end of grade 3 and identifies areas of strength and weakness.

There are four literacy tasks in the dataset:

  • Deletion: The child listens to a word and is then asked to delete a portion of the word and produce a new word (the target word). Measures a child’s phonological awareness skills.
  • Blending: The child listens to a word that is broken down into parts and is then asked to combine the sounds and say the target word. Measures a child’s phonological awareness skills.
  • Nonword repetition: The child listens to nonwords and repeats them back verbatim. Measures a child’s phonological working memory by asking them to repeat nonwords of increasing complexity.
  • Sentence repetition: The child listens to a sentence recorded on the tablet and then repeats the sentence verbatim. Assesses the child's ability to listen to and repeat sentences of varying length and complexities without changing the sentence’s structure or meaning.

iPad screenshots showing a blending task and a deletion task

iPad screenshots showing the view of the person administering and scoring the literacy screener.

Students were recruited to participate via their school and typically completed assessments twice during the school year, in the Fall and Winter. Some students completed the assessment at school, and others at home during the COVID-19 pandemic. The participants included students from diverse socioeconomic, ethnic, geographic, and racial backgrounds. Children were not assessed if they were not proficient in English, were in an exceptional student education classroom due to severe developmental or behavioral disabilities, or if their parents did not consent to participate in the study.

Recordings of students completing exercises were removed from the competition dataset if no voice activity was detected or if the file quality was poor. Additional task-specific criteria for excluding audio files (e.g. based on phoneme error rate or clip duration) were also applied.

About the sponsors


This project is sponsored by ReadNet, a multidisciplinary group of cognitive science, speech, education, and data science researchers. They have come together to solve a longstanding education issue: how do we identify children at risk for reading difficulty and intervene before this failure occurs. The collaborators are affiliates of the following research groups:

  • The Gabrieli Lab at MIT aims to understand how the human brain empowers learning, thinking, and feeling, and to use that understanding to help people live happier and more productive lives.

  • The Florida Center for Reading Research at FSU improves learning and achievement from birth through adulthood through rigorous and robust research, innovation, and engagement.

  • The Senseable Intelligence Group at MIT uses neuroimaging, speech communication, and machine learning to improve assessments and treatments for mental health, and neurological disorders.

Additional resources


For more information about literacy challenges in children, see:

If you're new to working with audio data, you might find the following to be helpful starting points: