MétaCan
Menu
Back to cohort

Centaur VGI: An Evaluation of Engagement, Speed, and Quality in Hybrid Humanitarian Mapping

2022· article· en· W6902062445 on OpenAlexaff

Bibliographic record

VenueFigshare · 2022
Typearticle
Languageen
FieldSocial Sciences
TopicGeographic Information Systems Studies
Canadian institutionsPublic Health Agency of Canada
Fundersnot available
KeywordsVolunteered geographic informationUsabilityWorkflowCrowdsourcingAutomationCitizen scienceQuality (philosophy)Data qualityOutsourcing

Abstract

fetched live from OpenAlex

Volunteered geographic information (VGI) is often cited as a potential solution to persistent global inequalities in map data, particularly in areas undergoing humanitarian crises. Poor volunteer engagement, slow data production, and low-quality outputs have limited progress, however, and can unintentionally exaggerate inequalities. Hybrid machine learning–VGI (ML–VGI) frameworks can help to overcome these challenges through a combination of workflow automation and purposive human input, but the use of these workflows is rare in practice. Here, we implement an ML–VGI framework (Centaur VGI) and undertake a detailed comparative usability assessment against an existing, widely used VGI mapping platform to demonstrate its potential to improve volunteer engagement, mapping speed, and data quality. Our results suggest that through automated building, searching, and labeling, the Centaur VGI platform provides greater usability, quicker data production, and improved data quality for most users. Consequently, we provide the first evidence that hybrid ML–VGI approaches can be used to facilitate increased public participation in humanitarian building mapping efforts and thus help reduce global inequalities in map 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 imitation

Not 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.

metaresearch head score (Codex)0.027
metaresearch head score (Gemma)0.085
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.027
Threshold uncertainty score0.141

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0270.085
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0040.004
Science and technology studies0.0010.002
Scholarly communication0.0060.005
Open science0.0030.008
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0070.002

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.

Opus teacher head0.328
GPT teacher head0.398
Teacher spread0.070 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueFigshareSame topicGeographic Information Systems StudiesFrench-language works237,207