Information retrieval of humanities resources: subject searching from a user perspective
Bibliographic record
Abstract
Purpose This paper explores the longstanding disconnect between Knowledge Organization (KO) and Information Retrieval (IR), advocating for their integration to improve subject access in humanities and cultural heritage (CH) collections, including newer types of collections, such as those of research data. Design/methodology/approach Through a critical synthesis of literature, standards and recent advances in both KO and IR, the paper identifies key advantages and challenges and proposes a collaborative research agenda to address them. Findings While KO Systems (KOS) provide semantic depth and contextual accuracy, and IR systems offer scalability, their independent development has limited the effectiveness of search systems for humanities and CH collections. Today’s operational search systems lack the capacity to support nuanced, exploratory search due to this disconnect. In addition, both KO and IR fields come with challenges which might be addressed via a complementary approach. The purposeful integration of KO and IR is necessary to address challenges such as opaque IR algorithms, underused or outdated KOS, and the need for context-aware, transparent and inclusive discovery environments. Practical implications Integrated KO-IR systems can support more accurate and inclusive discovery interfaces for libraries, museums and archives, as well as any search system, enhancing the visibility and usability of their resources. Originality/value The paper brings together perspectives from traditionally separate communities and calls for a de-siloed approach to designing subject access systems. It introduces key research questions and strategies for aligning KOS with advanced IR techniques.
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 | 0.009 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.006 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.019 | 0.020 |
| Open science | 0.001 | 0.005 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".