Big(ger) data as better data in open distance learning
Bibliographic record
Abstract
<p>In the context of the hype, promise and perils of Big Data and the currently dominant paradigm of data-driven decision-making, it is important to critically engage with the potential of Big Data for higher education. We do not question the potential of Big Data, but we do raise a number of issues, and present a number of theses to be seriously considered in realising this potential.</p><p>The University of South Africa (Unisa) is one of the mega ODL institutions in the world with more than 360,000 students and a range of courses and programmes. Unisa already has access to a staggering amount of student data, hosted in disparate sources, and governed by different processes. As the university moves to mainstreaming online learning, the amount of and need for analyses of data are increasing, raising important questions regarding our assumptions, understanding, data sources, systems and processes.</p><p>This article presents a descriptive case study of the current state of student data at Unisa, as well as explores the impact of existing data sources and analytic approaches. From the analysis it is clear that in order for big(ger) data to be better data, a number of issues need to be addressed. The article concludes by presenting a number of theses that should form the basis for the imperative to optimise the harvesting, analysis and use of student data.</p>
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 | 0.036 | 0.087 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.008 |
| Science and technology studies | 0.006 | 0.023 |
| Scholarly communication | 0.050 | 0.073 |
| Open science | 0.005 | 0.023 |
| Research integrity | 0.007 | 0.011 |
| Insufficient payload (model declined to judge) | 0.013 | 0.004 |
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".