Actionable companion · Motivation & engagement
Learning with agency: Building a responsive teacher: how temporal contingency of gaze interaction influences word learning with virtual tutors
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:
Animated pedagogical agents are lifelike virtual characters designed to augment learning. A review of developmental psychology literature led to the hypothesis that the temporal contingency of such agents would promote human learning. We developed a Pedagogical Agent with Gaze Interaction (PAGI), an experimental animated pedagogical agent that engages in gaze interaction with students. In this study, university students learned words of a foreign language, with temporally contingent PAGI (live group) or recorded version of PAGI (recorded group), which played pre-recorded sequences from live sessions. The result revealed that students in the live group scored considerably better than those in the recorded group. The finding indicates that incorporating temporal contingency of gaze interaction from a pedagogical agent has positive effect on learning.
What kind of evidence is this?
Conversational & pedagogical agents · Design requires full-text appraisal
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
Thirty participants (seven women) were recruited from a subject pool at the University of Tokyo. Their mean age was 20.19 (s.d.=1.47) years. Participants were all native Japanese without Korean language experience. An additional five participants were not included in the sample owing to the failure of the eye-tracking system during the experiment, which caused the agent to malfunction. Participants were randomly assigned to either live (n=15; women=4; mean age=20.0) or recorded (n=15; women=3; mean age=20.4) group.
Limitations and uncertainty · source passage
The analysis also showed that for the live group, excessive fixation duration was related to lower test scores. This is probably attributable to a lack of motivation. The participants may have thoughtlessly followed the instruction by exhibiting gaze behaviours, but did not invest full attention to word learning. If this was the case, fixation duration may be used to counter low attention in real world settings, especially for students with low motivation. To this end, how fixation duration is affected by motivation is an interesting research topic and requires future research.
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.
- Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
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
Hanju Lee; Yasuhiro Kanakogi; Kazuo Hiraki. Building a responsive teacher: how temporal contingency of gaze interaction influences word learning with virtual tutors. Royal Society Open Science (2015-01-14). https://doi.org/10.1098/rsos.140361
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.