Actionable companion · Assessment & reasoning

Learning with agency: Charting new territories: fuzzy systems in English language teaching and learning

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.

Read original paper Search paper agent CC BY 4.0

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): Secondary school, Higher education. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Abstract Background In reality, the English language is a mystery; despite its inherent worth and the advantages of fluency, there is a pervasive impression that English instruction in secondary schools is of low quality, contributing to students’ lack of proficiency in the language in higher education and beyond. Pedagogical approaches persist in the classroom, topic after subject, including English. Analyzing texts in great depth via translation and emphasizing vocabulary are joint exercises in English classes. Students waste a lot of time copying things off the board in English classes despite the growing recognition of the significance of both listening and speaking effectively. Methods The Fuzzy Bayesian Intelligent Tutoring System (FB-ITS) is an artificial intelligence (AI) system that adaptively supports students in English teaching and learning settings. It is built in this experimental research employing AI methodologies based on fuzzy logic and the Bayesian network methodology. Using conventional approaches that rely primarily on numerical scores to evaluate academics’ teaching and research activities at various levels is becoming increasingly challenging. Expert systems based on fuzzy logic, suggested in this study, can handle teacher and student evaluations even when faced with imprecise information and uncertainty; this is necessary since academic performance is being indexed in multiple international databases using impact indices at different scales. Results The results showed that, on average, students using the FB-ITS took less time to complete the post-test than students using the conventional e-learning system. This research proposes an English teaching and learning approach that has been very successful based on experimental findings of related big data clustering algorithms. The assessment accuracy has risen by 4%, and the teaching resource utilization rate has been increased by 5%. Keywords: English teaching, English learning, Fuzzy logic, Bayesian networks, Students

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Comparative / pre-post study reported

Stage: Secondary school; 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

A thorough comparative study assessed the accuracy, flexibility, and learning efficiency of the proposed FB-ITS model compared to other intelligent tutoring systems. By reducing reaction time for adaptive exercise creation by 20% and improving error classification accuracy by 15%, FB-ITS surpasses conventional models such as rule-based systems and simple Bayesian networks. Compared to baseline systems, the fuzzy-Bayesian hybrid model had a 25% higher learner advancement rate, demonstrating improved flexibility. Pairwise t-tests were used to verify statistical significance, which confirms that the suggested method is robust. Experiments using separate experimental and control groups yielded the claimed gains in assessment accuracy (4% improvement) and instructional resource utilization rate (5% improvement). One hundred students participated in the study using the suggested FB-ITS model, whereas one hundred students in the control group used more conventional rule-based tutoring methods. Both groups were a perfect fit regarding age, level of language competence, and learning goals. Over 12 weeks, participants were asked to complete a battery of standardized tests and activities. Extensive records of system interactions, precision in exercise completion, and access to instructional resources were used to compute the measures. To confirm the findings and ensure the improvements were reliable and statistically significant, paired t-tests and other analyses were conducted.

Limitations and uncertainty · source passage

The quantity and quality of the training data are the primary determinants of the system’s performance. Low or biased datasets could make the system less flexible in adapting to different learning situations, which might result in incorrect predictions or suggestions. For another, it could be challenging to execute in real-time or with limited resources when fuzzy logic and Bayesian inference are combined because of the computational complexity this might bring. Third, the system may have trouble learning languages with subtle nuances or context-specific mistakes since these situations often demand human judgment, which is hard to simulate computationally.

Design the system before the pilot

Document the learner model, mastery rule, hint sequence and adaptation signal. Compare adaptive routing with the same content in a non-adaptive sequence. Check whether early errors lead to persistent low-expectation pathways.

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. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. 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. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. 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

Xiaomei Wen; Deng Pan. Charting new territories: fuzzy systems in English language teaching and learning. PeerJ Computer Science (2025-07-31). https://doi.org/10.7717/peerj-cs.2887

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.