Abhinav Chand, Arpan Pal, Moyi Tian, Zhaobidan Feng, Mengting Chao
The group of students learning English as a second language, known as English Language Learners (ELLs), has rapidly grown. While automated feedback tools make it easier for teachers to assign more writing tasks, they are not designed with ELLs in mind. Existing tools are unable to provide feedback based on the language proficiency of the student, resulting in a final evaluation that may be skewed against the learner. We hope to improve automated feedback tools to better support the unique needs of these learners. We utilize a dataset of argumentative essays written by 8th-12th grade ELLs to develop English language proficiency evaluation models, which help ELLs receive more accurate feedback on their language development and expedite the grading cycle for teachers.