Towards predicting student learning outcomes from learning management system interactions using machine learning
Bibliographic record
Abstract
Advancements in classroom technology have resulted in new types of data collection in educational settings. Along with improvements in the fields of artificial intelligence and machine learning, this educational data can be used to study how we learn and create more personalised learning environments. Starting in March 2020 all in-person courses were abruptly moved to remote instruction in order to combat the COVID-19 pandemic. This influx of students taking remote courses presented a new opportunity to study how students interact with course materials. Remote learning courses at the University of Manitoba are offered using a learning management system (LMS) that centralizes all course activities and files and records user-activities. The use of machine learning techniques with education-based data is an emerging discipline that offers an opportunity to provide new insights in this area. This thesis presents a code-based tool to create student timelines from raw LMS date-time stamp data and extract features describing student behaviours within a single-term online course. The successes and limitations of these features to predict student grade outcomes were investigated using supervised and unsupervised machine learning models. The LMS data was also explored using neural network-based CNNs and transformers. The experiments presented in this thesis indicate that students predominately interact with the system at the same time on any given day relative to their previous interaction. The results further demonstrate that temporal features created from LMS interactions can predict student outcomes with greater than random accuracy. The neural network-based classifiers produced more accurate student outcome predictions than the feature-based ML models at the expense of interpretability. This thesis contributes to the body of knowledge on student modelling and prediction, as well as student behaviour within an LMS in an online course, and suggests that educators can help to reduce students' cognitive load and improve students' learning by updating the LMS at a consistent time of day.
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 | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".