Introducing the INSPIRE Framework: Guidelines From Expert Librarians for Search and Selection in HCI Literature
Bibliographic record
Abstract
Abstract Formalized literature reviews are crucial in human–computer interaction (HCI) because they synthesize research and identify unsolved problems. However, current practices lack transparency when reporting details of a literature search. This restricts replicability. This paper introduces the INSPIRE framework for HCI research. It focuses on the search stage in literature reviews to support a search that prioritizes transparency and quality-of-fit to a research question. It was developed based on guiding principles for successful searches and precautions advised by librarian experts in HCI (n=8) for search strategies in (primarily systematic) literature reviews. We discuss how their advice aligns with the HCI field and their concerns about computational AI tools assisting or automating these reviews. Based on their advice, the framework outlines pivotal stages in conducting a literature search. These essential stages are: (1) defining research goals, (2) navigating relevant databases and (3) using searching techniques (like divergent and convergent searching) to identify a set of relevant studies. The framework also emphasizes the importance of team involvement, transparent reporting, and a flexible, iterative approach to refining the search terms.
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 | 0.478 | 0.550 |
| Meta-epidemiology (narrow) | 0.004 | 0.006 |
| Meta-epidemiology (broad) | 0.006 | 0.008 |
| Bibliometrics | 0.049 | 0.027 |
| Science and technology studies | 0.008 | 0.010 |
| Scholarly communication | 0.023 | 0.023 |
| Open science | 0.013 | 0.024 |
| Research integrity | 0.015 | 0.010 |
| Insufficient payload (model declined to judge) | 0.013 | 0.012 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".