Improving EFL Students’ Speech Proficiency Through AI-Driven Interaction: A Study on ChatGPT’s Impact
Bibliographic record
Abstract
This study explored how ChatGPT can help students improve their English speech proficiency skills, especially in speaking. The main objectives were to investigate the improvement of the participants’ speech proficiency after using ChatGPT treatment and how they perceive the implementation of ChatGPT in improving speech proficiency. A mixed-methods approach was adopted in this study and participants were chosen using a purposive sampling technique. The study focused on the benefits and limitations of using AI tools in education. A gap was found in previous research, as many studies discussed ChatGPT’s features, but few focused on how students feel about using it in real classrooms. The data were collected through a survey questionnaire and semi-structured interviews. Results showed that many students found ChatGPT to be a beneficial process in the development of students’ speech, as an easy-to-use and helpful tool for learning English. The study revealed that ChatGPT training significantly improved students’ speech performance (t = 12.538, p < .05), enhancing their content, fluency, language and style through AI-assisted feedback that reduced anxiety and promoted autonomous learning. In addition, results show that students highly valued ChatGPT’s timely and effective feedback on speech tasks, earning an overall mean of 4.39, recognizing it as a reliable support tool that enhances revisions, reduces anxiety, saves time, and promotes motivation. This implies that teachers can integrate ChatGPT into speaking activities to provide quick feedback and build students’ confidence, making learning more engaging.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".