Outcomes

ChatGPT Supporting Heritage Language Literacy in Underserved Communities: A Neurocognitive Study of Sociolinguistic Factors

To explore AI-assisted literacy development in Heritage Language (HL) learning, the University of Alabama at Tuscaloosa has launched a seed-funded pilot study focusing on Chinese Heritage Language (CHL) learners in the American South. See the research report here: https://www.degruyterbrill.com/document/doi/10.1515/dsll-2024-0011/html

This project responds to a growing need for innovative educational interventions in underserved regions like Alabama, where Spanish, Chinese, and Gujarati constitute the three largest HL groups. Despite some parental investment and little governmental support in HL programs and schooling, most K-16 heritage language learners have a disparity between oracy, literacy, and overall HL proficiency. This study investigates how generative AI tools, specifically ChatGPT, can provide customized, real-time support for CHL learners to strengthen literacy outcomes. Through prompt-engineered leading protocols (PLP) and prompt engineering techniques (PET), participants at beginning, intermediate, and advanced levels will engage with AI-generated reading materials designed to match their linguistic proficiency and learning goals. The study employs longitudinal, mixed methods including surveys, learner intervention, and periodic EEG assessments, to analyze the influence of sociocultural and cognitive factors on HL learners’ progress in the American South.

Project updates will be shared across various publications as development progresses through its different stages.

For questions on the study, please email Dr. Xiang Zhang, Ph.D., xiang.zhang@ua.edu.