Mining the Past – Data-Intensive Knowledge Discovery in the Study of Historical Textual Traditions
Bibliographic record
Abstract
Text-heavy and unstructured data constitute the primary source materials for many historical reconstructions. In history and the history of religion, text analysis has typically been conducted by systematically selecting a small sample of texts and subjecting it to highly detailed reading and mental synthesis. But two interrelated technological developments have rendered a new data-intensive paradigm—one that can usefully supplement qualitative analysis—possible in the study of historical textual traditions. First, the availability of significant computing power has made it possible to run algorithms for automated text analysis on most personal computers. Second, the rapid increase in full text digital databases relevant to the study of religion has considerably reduced costs related to data acquisition and digitization. However, a limited understanding of the scope, advantages, and limitations of data-intensive methods, combined with an overly enthusiastic praise of big data by policy-makers and data scientists, have created real obstacles to the implementation of this paradigm in historical research. This is unfortunate, because history offers a rich and uncharted field for data-intensive knowledge discovery, and historians already have the much sought after and necessary domain expertise. In this article we seek to remove obstacles to the data intensive paradigm by presenting its methods and models for handling text-heavy data.
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 | 0.014 | 0.042 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.009 | 0.008 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.007 | 0.012 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".