Everyone's Invited: A New Paradigm for Evaluation on Non-Transferable Datasets
Bibliographic record
Abstract
Social media data mining and analytics has stimulated a wide array of computational research. Traditionally, individual researchers are responsible for acquiring and managing their own datasets. However, the temporal nature of social data, the challenges involved in correctly preparing a dataset, the sheer scale of many datasets, and the proprietary nature of many data sources can make extending and comparing computational methods difficult and often impossible. In light of this, because replicability is a fundamental pillar of the scientific process and because method comparison is essential to characterizing computational advancements, we require an alternative to the traditional model of researcher-owned datasets. In this paper we propose FREESR, a framework that gives researchers the ability to develop and test method performance without requiring direct access to “shared” datasets. As a case study and first community resource, we have implemented the FREESR paradigm around the task of Tweet geolocation. The implementation showcases the clear suitability of this framework for the social media research context. Beyond the implementation, we see the FREESR paradigm as being an important step towards making study reproducibility and method comparison more principled and ubiquitous in the social media research community.
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 | 0.280 | 0.393 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.005 |
| Bibliometrics | 0.007 | 0.007 |
| Science and technology studies | 0.005 | 0.008 |
| Scholarly communication | 0.012 | 0.025 |
| Open science | 0.008 | 0.021 |
| Research integrity | 0.007 | 0.009 |
| 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".