Students raised concerns that performance forecasts cannot capture personal circumstances affecting study¶

Claim · All claims
Evidence · 1 study · qualitative r3 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q2 i? Some students questioned the validity of predictive data because forecasts cannot capture the impact of personal conditions and unforeseen life events on performance. → Herodotou 2025

Evidence¶

Herodotou 2025¶

Herodotou, C., Shrestha, S., Comfort, C., Andrews, H., Mulholland, P., Bayer, V., Maguire, C., Lee, J. & Fernandez, M. (2025). A Participatory Approach to Designing a Student-Facing Dashboard for Online and Distance Education. Journal of Learning Analytics, 12(2). https://doi.org/10.18608/jla.2025.8481

q2 · i? · qualitative · r3

Thematic analysis of focus group Activity 2 discussions (20 students) produced themes on predictive data, including contextual information limits and suggestions that forecasts cover the whole module. One student noted being in hospital yet performing well. The article reports "predictions not being able to capture the context of studying."

"students raised some concerns regarding predictions not being able to capture the context of studying and the potential impact of personal conditions on performance."

Discussion¶

Related Claims¶

• Deep Knowledge Tracing has a fundamental limitation that prevents it from supporting mastery learning on multi-step problems — related
• Teachers reported validity, subjectivity, and feasibility concerns in assessing communication and digital literacy — related
• Teacher expectation bias predicted Dutch secondary students' performance up to five years later, after controls for prior achievement, IQ and motivation, in one large correlational cohort study — related
• A K-3 school-level growth measure was estimated and examined, with validity and precision concerns suggesting cautious use for accountability — related
• Prediction algorithms forecast student achievement from small windows of data, more accurately when data are enriched with instructional design and learning-process detail — related
• Engagement inferred from log data must be treated with caution because digital traces reflect unevenly distributed social and material conditions — related
• Both students and teachers believe AI cannot capture social dynamics and emotional feelings, but only teachers additionally feared AI use would reduce interpersonal interactions in class — related
• Mental tests have decided limitations: they miss motivation, persistence, and emotional life, and intelligence ratios are subject to change — related