Maitree Shah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maitree Shah has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Clarissa Hin-Hei Lau
Department of Surgery, Faculty of Medicine and Health Sciences, McGill University, Montreal General Hospital, Montreal, Canada
1 shared publication Eunice Eunhee Jang
Applied Psychology and Human Development, University of Toronto, Toronto, ON, Canada
1 shared publication- Eunice Eunhee Jang
University of Toronto, Canada
1 shared publication - Liam Hannah
Ontario Institute for Studies in Education University of Toronto Toronto Ontario Canada
1 shared publication - Melissa R. Hunte
Lunenfeld-Tanenbaum Research Institute, Sinai Health, Toronto, Canada
1 shared publication - Samantha McCormick
Ontario Institute for Studies in Education, University of Toronto
1 shared publication
Latest Publications
- Top Cited Papers
- 20 October 2023
- Published by Taylor & Francis in Language Assessment Quarterly
- Vol. 20 (4-5) , 399-420
Validity Arguments for Automated Essay Scoring of Young Students’ Writing Traits
- 20 October 2023
- Published by Taylor & Francis in Language Assessment Quarterly
- Vol. 20 (4-5) , 399-420
Top Cited PapersValidity Arguments for Automated Essay Scoring of Young Students’ Writing Traits
- 4 July 2021
- Published by Taylor & Francis in Assessment in Education: Principles, Policy & Practice
- Vol. 28 (4) , 477-505
Investigating the potential of NLP-driven linguistic and acoustic features for predicting human scores of children’s oral language proficiency
Children’s oral language proficiency (OLP) is integral for developing literacy skills. Storytelling or retelling is often used by parents and educators to elicit children’s OLP, yet it is less commonly used for assessment purposes. Leveraged by natural language processing and machine learning, this study examined the extent to which computational linguistic and acoustic indices predict human ratings of children’s (n=184 aged 9 to 11) OLP using two story retell stimuli presented in written and aural forms. Human raters scored children’s OLP on five oral proficiency criteria: vocabulary, grammar, idea development, task-fulfilment, and speech delivery, using a 4-point scale, and linguistic and acoustic features were used to predict each criterion. Results showed the efficacy of automated indices to predict human scores of children’s OLP. This study calls for attention to discrepancies in human and machine speech delivery scores and stimulus effects on story retelling performance among children of different language backgrounds.
- 4 July 2021
- Published by Taylor & Francis in Assessment in Education: Principles, Policy & Practice
- Vol. 28 (4) , 477-505
Investigating the potential of NLP-driven linguistic and acoustic features for predicting human scores of children’s oral language proficiency
Children’s oral language proficiency (OLP) is integral for developing literacy skills. Storytelling or retelling is often used by parents and educators to elicit children’s OLP, yet it is less commonly used for assessment purposes. Leveraged by natural language processing and machine learning, this study examined the extent to which computational linguistic and acoustic indices predict human ratings of children’s (n=184 aged 9 to 11) OLP using two story retell stimuli presented in written and aural forms. Human raters scored children’s OLP on five oral proficiency criteria: vocabulary, grammar, idea development, task-fulfilment, and speech delivery, using a 4-point scale, and linguistic and acoustic features were used to predict each criterion. Results showed the efficacy of automated indices to predict human scores of children’s OLP. This study calls for attention to discrepancies in human and machine speech delivery scores and stimulus effects on story retelling performance among children of different language backgrounds.