Actionable companion · Feedback & scaffolding
Learning with agency: Reducing anxiety and enhancing performance: the impact of AI chatbots versus human facilitation on EFL speaking assessment outcomes
AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.
Evidence and context
Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education. Verify the participant population and task before transferring the findings.
Original authors’ abstract, reproduced under the linked source license:
Introduction This study investigates the comparative impact of artificial intelligence (AI) chatbots and human facilitation on foreign language speaking anxiety and achievement scores among 48 first-year English Language Teaching students at a Turkish public university. Methods Using a mixed-methods approach, we administered two comparable speaking examinations—one facilitated by an AI chatbot and the other by human instructors—with Foreign Language Speaking Anxiety Scale assessments preceding each exam. Additionally, students completed a digital literacy assessment to determine technological proficiency levels. Semi-structured interviews provided qualitative insights into student experiences. Results Results revealed a significant negative correlation between speaking anxiety and achievement scores in human-facilitated examinations (r = −0.500, p 0.01), suggesting AI’s potential in mitigating anxiety effects. While achievement scores did not significantly differ between test conditions, students with higher digital literacy performed better in AI-facilitated examinations (r = 0.353, p < 0.05). Thematic analysis of qualitative data revealed four major themes: self-perceived speaking proficiency, comparative perceptions of AI versus human evaluation, intentions for future classroom implementation, and feedback quality assessment. Discussion The findings contribute to the theoretical understanding of technology-mediated assessment in foreign language education and offer practical implications for creating anxiety-reduced assessment environments. Notably, this study extends current research by addressing cross-cultural considerations in AI assessment implementation and examining how technological familiarity influences assessment experiences across diverse educational contexts.
What kind of evidence is this?
Conversational & pedagogical agents · Qualitative / mixed methods
Stage: Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.
Study methods · source passage
The study involved 48 first-year undergraduate students (29 female, 19 male; age range 18–22 years) enrolled in the English Language Teaching (ELT) program at a public university in Turkey. All participants were in their second semester of study and had completed at least one speaking-focused course as part of their curriculum. This ensured that participants possessed sufficient English speaking experience to engage meaningfully with the assessment tasks.
Limitations and uncertainty · source passage
Several limitations of this study should be acknowledged when interpreting its findings. First, the sample size (N = 48) and convenience sampling approach limit the generalizability of results to broader populations. Future research should employ larger, more diverse samples and random sampling techniques to enhance external validity.
Design the system before the pilot
Define whether the agent asks questions, gives hints, explains or assesses. Test hallucinated feedback, excessive praise, misleading confidence and responses when the learner is confused. A conversational interface alone does not establish autonomous agency.
- Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
- Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.
A 90-day district pilot
- Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
- Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
- Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
- Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.
The board decision brief
Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.
Attribution and reuse
Zafer Susoy. Reducing anxiety and enhancing performance: the impact of AI chatbots versus human facilitation on EFL speaking assessment outcomes. Frontiers in Psychology (2026-01-12). https://doi.org/10.3389/fpsyg.2025.1745942
Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.