Research map / Label-efficient and robust learning / Semi-supervised learning
Discriminating Cognitive Disequilibrium and Flow in Problem Solving: A Semi-Supervised Approach Using Involuntary Dynamic Behavioral Signals
Mononito Goswami, Lujie Chen, Artur Dubrawski
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use deep embedding features instead of complexity measures (ablation) | random forest, non-personalized · LOPO | AUC: 0.43 -> 0.79 | Improved |
| use deep embedding features instead of complexity measures (ablation) | random forest, non-personalized · Random split | AUC: 0.72 -> 0.83 | Improved |
| use deep embedding features instead of complexity measures (ablation) | random forest, personalized · LOPO | AUC: 0.55 -> 0.74 | Improved |
| add feature personalization to deep embeddings (ablation) | random forest · LOPO | AUC: 0.79 -> 0.74 | Mixed |
| add feature personalization to deep embeddings (ablation) | random forest · Random split | AUC: 0.83 -> 0.8 | No clear effect |
| add feature personalization to complexity measures (ablation) | random forest · LOPO | AUC: 0.43 -> 0.55 | Improved |
| add feature personalization to complexity measures (ablation) | random forest · Random split | F1: 0.71 -> 0.71 | No clear effect |
| evaluate on unseen subjects (LOPO) instead of random split | deep embedding, non-personalized · accuracy | Accuracy: 0.82 -> 0.7 | Hurt |
| evaluate on unseen subjects (LOPO) instead of random split | deep embedding, non-personalized · AUC | AUC: 0.83 -> 0.79 | Hurt |
| evaluate on unseen subjects (LOPO) instead of random split | complexity, non-personalized · accuracy | Accuracy: 0.71 -> 0.5 | Hurt |
| replace supervised ResNet with semi-supervised deep embedding model | semi-supervised model · LOPO | AUC: 0.73 -> 0.79 | No clear effect |
| replace supervised ResNet with semi-supervised deep embedding model | semi-supervised model · LOPO | Accuracy: 0.78 -> 0.7 | Hurt |
Closest papers by meaning
- Boosting Neural Cognitive Diagnosis with Student’s Affective State Modeling (AAAI 2024 · similarity 0.87)
- CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention (ICML 2025 · similarity 0.85)
- FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition (NeurIPS 2025 · similarity 0.84)
- From Raw Video to Pedagogical Insights: A Unified Framework for Student Behavior Analysis (AAAI 2024 · similarity 0.84)
- Enhancing Cognitive Diagnosis Using Un-interacted Exercises: A Collaboration-Aware Mixed Sampling Approach (AAAI 2024 · similarity 0.83)
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
