Agentic education · Learning science

Actionable companion · Motivation & engagement

Learning with agency: A process‐oriented perspective on pre‐service teachers' self‐efficacy and their motivational messages: Using large language models to classify teachers' speech

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 paperSearch paper agentCC 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): Age / stage not established. Verify the participant population and task before transferring the findings.

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

Abstract Background Recent studies have examined the relation between teacher motivation, motivational messages and student learning but are limited to an achievement‐related context, primarily using survey data. Moreover, our understanding of the relation between various teacher characteristics, such as teacher self‐efficacy (TSE), and their motivational message use remains limited. Aims Our study tested whether teacher speech can be classified into self‐determination (SDT)‐based motivational messages and reliably assessed with a large language model (LLM). Additionally, we analysed the relation between pre‐service TSE and their motivational message use. Sample For our first aim, we used human‐rater annotations from 119 pre‐service teachers' classroom recordings. For our second aim, we used data from 103 pre‐service teachers (52.69% female; M age = 22.98, SD age = 3.26, Min age = 19, Max age = 34) who participated in a survey and were video‐recorded while teaching. Methods First, we manually classified pre‐service teachers' motivational messages based on transcripts and used human‐rater annotations to fine‐tune an LLM. Second, we analysed the relation between pre‐service TSE and motivational message use. Results and Conclusions The fine‐tuned LLM demonstrated promising performance in assessing SDT‐based motivational messages but needs further refining to assess thwarting messages. The analysis with human annotation showed that pre‐service TSE for classroom management positively affected the frequency of relatedness‐supportive messages. Pre‐service TSE for student engagement increased the likelihood of never using a competence‐ or relatedness‐thwarting message. Pre‐service TSE for instructional strategies reduced the frequency of autonomy‐supportive messages. LLM‐based analyses showed slightly different results but did not contradict human annotation‐based analyses. Keywords: artificial intelligence, large language models, motivational messages, self‐determination theory, teacher self‐efficacy

What kind of evidence is this?

Supporting AI learning science · Survey / observational study

Stage: Age / stage not established. 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

In this study, we investigated the above two research questions with two cohorts of pre‐service teachers. Figures A1 and A2 in Appendix A illustrate the pipeline of both research questions. To evaluate the reliability of an LLM for assessing pre‐service teachers' motivational messages, video data from 119 recorded lessons of pre‐service teachers were used. To investigate the relations between pre‐service TSE beliefs and their use of motivational messages, a sample of 103 pre‐service teachers (52.69% female; M age = 22.98, SD age = 3.26, Min age = 19, Max age = 34) was considered. These pre‐service teachers had video‐recorded their lessons and completed a survey on their motivational beliefs, except for 10 participants who did not fill out the questionnaire. Pre‐service teachers were on average in their fifth semester (SD = 1.81, Min = 2, Max = 15) and the majority were born in Germany (90.55%). Of this sample, the three most studied subjects were German (15.20%), English (12.25%) and Physical Education (9.31%). The study obtained ethical approval from the university ethics committee (protocol no. 41/2023).

Limitations and uncertainty · source passage

Regarding our second research question, the sample size of pre‐service teachers considered was comparatively small, which led to low statistical power for testing. However, despite the suboptimal statistical power, we were still able to identify substantial effects of pre‐service TSE on their motivational messages. Further studies are needed to validate our findings using larger data sets. Additionally, our study did not account for the speaker's tone of voice, although research has shown that a controlling tone of voice increases listeners' sense of pressure, decreases their willingness to cooperate and creates a sense of distance, regardless of the message (Vrijders et al., 2024). In this study, we focused on pre‐service teachers in a Bachelor programme. Although it could be assumed that pre‐service teachers have limited practical experiences and thus their self‐efficacy beliefs might not realistically reflect their skills (for further discussion, see Klassen & Chiu, 2011), prior work has shown that pre‐service TSE for student engagement positively predicts observer‐rated emotional support during practical teaching experiences in schools (Hußner et al., 2024). Thus, it can be assumed that even in early stages of pre‐service teachers' studies, their self‐efficacy already affects how they teach in class. Moreover, the pre‐service teachers in our study participated in a course on motivation‐enhancing teaching practices before teaching a lesson in a secondary school. The specific study context and the course materials they engaged with prior to teaching may have influenced their instructional practices and the motivational messages they employed in the class. To gain a clearer understanding of how pre‐service TSE affects the motivational messages these pre‐service teachers use, a control group of pre‐service teachers who have not engaged with course materials on motivation‐enhancing teaching would be required.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
  • 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

  1. 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.
  2. Days 16–30 · Design. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. 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.
  4. Days 61–90 · Decide. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. 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

Olivia Metzner; Yindong Wang; Wendy Symes; Yizhen Huang; Lena Keller; Gerard de Melo; Rebecca Lazarides. A process‐oriented perspective on pre‐service teachers' self‐efficacy and their motivational messages: Using large language models to classify teachers' speech. The British Journal of Educational Psychology (2025-04-28). https://doi.org/10.1111/bjep.12779

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.