A complex dynamical system approach to student engagement
Bibliographic record
Abstract
Multimodal data analysis has been approached through three main avenues: (1) joint effect approach, (2) triangulation approach, and (3) separate latent construct approach. While these approaches have advanced our understanding of the learning process, they fail to capture its dynamic and emergent nature. This study examines multimodal data through the lens of complex dynamical system (CDS) approach. We investigated whether a CDS approach could provide unique insights into predicting and understanding cognitive engagement during learning. The participants comprised 61 third-year medical students (47.5 % females). From a CDS perspective, we analyzed eye gaze, head pose, and facial action units of participants engaged in an interactive learning environment. We found that specific parameters of eye gaze, head pose, and facial expressions significantly predicted cognitive engagement levels. Network density was also identified as a significant predictor of cognitive engagement. Notably, network density explained a greater proportion of the variation in cognitive engagement compared to any other individual variable considered. Additionally, we found that students in the low engagement group demonstrated consistently weak but stable interconnections among behavioral indicators, while the high engagement group displayed tightly clustered interaction patterns among variables. These findings highlight the added value of a CDS approach for modeling the dynamic complexity of cognitive engagement. This study represents a significant step in rethinking the research agenda in multimodal learning analytics. Methodologically, this study demonstrates the potential of CDS-based analytical techniques for gaining insights into physiological and psychological processes underlying engagement and learning. • We synthesize three motives for analyzing multimodal data about learning. • This study introduces a novel approach for analyzing multimodal data of engagement. • We analyzed eye gaze, head pose, and facial action units from 62 students. • A complex dynamical system approach provides additional insights into engagement. • This study contributes significantly to the field of multimodal learning analytics.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".