l2-writing
Filtering by topic l2-writing(4)Clear all filters
- PaperSystemForthcoming · 1 Aug 2026
The effects of collaborative planning on CALF metrics and textual coherence in L2 writing under varying task complexity
Chongrui He, Eerdemutu Liu
The study investigates how collaborative planning influences CALF (complexity, accuracy, lexical diversity, fluency) metrics and textual coherence in second language writing, and whether task complexity moderates these effects.
- PaperSystemForthcoming · 1 Aug 2026
Translanguaging optimizes the developmental trajectory of beginning-level L2 writing: A sequence analysis study with an experimental design
Muzi Li, Yunlu Zhao
This experimental study using sequence analysis found that translanguaging optimizes the developmental trajectory of beginning-level second language writing.
- PaperSystemForthcoming · 1 Aug 2026
Assessing L2 legal writing through a plain English lens: Insights on complexity, accuracy, and fluency
Yiran Xu, Xiaowan Zhang, J. Elliott Casal
This study examines the assessment of second language (L2) legal writing by applying plain English principles to evaluate complexity, accuracy, and fluency.
- PaperReCALL2 Mar 2026
Evaluating GPT-generated feedback for beginning-level Spanish writing: An exploratory study
Alyssia Miller De Rutté, Maite Correa
A task-customized GPT model was evaluated for assessing A1-level Spanish learners' writing and providing feedback. The model showed moderate score alignment with human raters but delivered inconsistent qualitative feedback, often vague or inaccurate. The study concludes that AI is not yet a viable standalone substitute for human evaluation in L2 writing instruction.
Original abstract
Feedback is integral to second language (L2) writing instruction. However, large class sizes and limited teacher time often challenge the delivery of personalized feedback, prompting interest in AI-powered solutions such as ChatGPT (Escalante et al., 2023; Huete-García & Tarp, 2024; Steiss et al., 2024; Yoon et al., 2023; Zhang, 2024). This study evaluates a task-customized GPT model, “Belinda,” trained to assess A1-level Spanish learners’ writing and provide feedback. Two research questions guided the investigation: (1) Can Belinda accurately score beginner Spanish writing using a provided rubric? (2) Can Belinda deliver constructive qualitative feedback? Human and GPT-generated scores were compared for inter- and intrarater reliability, and qualitative analyses categorized the feedback for usability in the classroom. Results revealed moderate alignment between Belinda’s scores and human raters, though reliability of the GPT fell short of calibration benchmarks. Feedback quality varied, with Belinda often providing vague, incomplete, or inaccurate suggestions. Despite iterative training, the GPT struggled to balance error correction with encouragement, a critical need for novice learners. Additionally, inconsistencies in identical GPT versions raised concerns about reliability. While Belinda showed potential in automating feedback, its limitations in accuracy, contextual understanding, and positivity suggest it is not yet a viable substitute for human evaluation by itself. These findings emphasize the challenges of integrating AI into L2 instruction and call for the need for extensive datasets, robust training, and human–AI collaboration to achieve pedagogically sound outcomes. Future research should explore hybrid feedback models and scalable solutions to enhance AI’s role in language education without compromising learner progress or confidence.