Generalizable detectors of students' affective states in DLPs remain an unsolved problem¶

Claim · All claims
Evidence · 1 study · theoretical r2 · q1
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person · recheck by 2027: tool and model accuracy changes quickly

Subclaims¶

q1 i? Although affective detectors have been built for specific platforms, no generalizable approach exists to date for detecting students' affective states such as boredom in DLPs, per Baker's (2019) keynote challenge to the community. → affective-detectors

Evidence¶

affective-detectors¶

Schellinger, A., & Roschelle, J. (2024, January). Looking Back to Move Forward. Digital Promise. https://doi.org/10.51388/20.500.12265/203

q1 · i? · theoretical · r2

This is the article's report of Baker's (2019) LAK keynote challenge to the learning analytics community — an authorially reported claim, not a new study; no effect size or data are printed.

"One unsolved problem is creating generalizable "detectors" of students' affective states, such as boredom, while they use a DLP. Knowing when a student is bored with educational content in a DLP could allow for targeted interventions to improve their engagement and effort, and although affective detectors have been built for specific platforms, no generalizable approach exists to date."

Discussion¶

Related Claims¶

• No significant impact of frustration or boredom (or anxiousness, discouragement, distractedness) on practice performance was found — related
• Enriched DLP data enable two types of theory testing: sustained observation of individuals in a single setting and modeling the same type of learner across contexts — related
• EDM methods have enabled real-time inference of a broader range of student attributes, including gaming the system, self-efficacy, off-task behavior, boredom, and frustration — related
• Student disengagement in adaptive learning platforms is linked to technical problems, boredom with long or irrelevant content, insufficient challenge and feedback, and declining engagement over time — related
• Automated gaming-the-system detectors built with XGBoost reliably recognize gaming in both problem-solving and self-explanation steps — a narrower finding that bears on this claim
• Frustration at not understanding a concept is perceived to motivate exploration and persistence, while frustration attributed to teachers or curriculum impairs motivation — related