Enhancing English Proficiency Through AI Conversations: The Impact of ChatGPT on TOEIC and Speechace Performance in a Project-Based Learning Context
Bibliographic record
Abstract
This study examined the impact of integrating ChatGPT into a project-based English learning course on students’ English proficiency, as assessed by TOEIC Listening and Reading scores and Speechace metrics. The participants, 110 first- and second-year university students, were divided into Homework and No-Homework groups, with the former required to engage in weekly English conversations with ChatGPT. The results revealed that while the Homework group demonstrated significant improvements in several Speechace categories, particularly among second-year students, no significant correlation was found between the number of completed assignments and score improvements. Additionally, TOEIC scores indicated greater progress in Listening and Reading among the Homework group compared to the No-Homework group. Notably, the reliance on text during ChatGPT conversations possibly explained the stronger impact on Reading and Vocabulary, while Fluency and Pronunciation also improved. However, an increase in unnatural pauses highlighted the need for further refinement in task design to encourage more natural conversational dynamics. This study underscored the potential of AI tools like ChatGPT to enhance English communication skills while identifying areas for improvement in their pedagogical application.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".