An End-to-End Human-Centered Automation of a Collaborative Analysis Platform
Bibliographic record
Abstract
Interactive machine learning (iML) integrates human insight into automated analysis to facilitate advanced knowledge discovery. However, state of the art in iML techniques face two significant difficulties, which hinder an end-to-end automation in such integration. One difficulty is to address different analysis requirements of individuals (i.e., users); another difficulty is to handle various experience levels of the users. These difficulties become profound in collaborative analysis, in which users work together for knowledge discovery. To overcome these difficulties, we present a novel iML scheme of adapting automated analysis workflows to user interactions. This scheme models the priority of tasks, which constitute an automated workflow. Taking account of the users' analysis objectives, the modelling incorporates implicitly their requirements based on their past and current interactions with task outputs. Moreover, the modelling exploits collective knowledge within user groups as well as document databases to map task relevance to the objectives. This human-centered modeling ensures that no explicit user intervention is necessary to adapt the workflows. Furthermore, the degree of the adaptation incorporates varying experience levels of the users, which is deduced from their interactions. Thus, our iML scheme enables an end-to-end automation of analysis workflows. For a preliminary assessment of the scheme, we have designed an emulator of user interactions to generate various scenarios of collaborative analysis. We observed that the scheme exhibited desired adaptation to varying user interactions. The adaptation took a short computation time to ensure the targeted end-to-end automation. These findings show the potential of deploying the proposed fully automated iML scheme in practice.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".