MétaCan
Menu
Back to cohort
Record W3194827031 · doi:10.1177/14614448211038761

Using social media images as data in social science research

2021· article· en· W3194827031 on OpenAlexafffund
Yan Chen, Kate Sherren, Michael Smit, Kyung Young Lee

Bibliographic record

VenueNew Media & Society · 2021
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsDalhousie University
FundersSocial Sciences and Humanities Research Council of CanadaNova Scotia Research Innovation Trust
KeywordsSocial mediaData scienceThematic analysisComputer scienceSocial researchCoding (social sciences)NarrativeThematic mapSociologySocial scienceQualitative researchWorld Wide Web

Abstract

fetched live from OpenAlex

We conducted a scoping review to identify and describe trends in the use of social media images as data sources to inform social science research in published articles from 2015 to 2019. The identified trends include the following: (1) there is increasing interest in social media images as research data, especially in disciplines like sociology, cultural studies, communication and environmental studies; (2) the photo sample size is often smaller than that is typically used in text-based social media analysis and usually is collected manually; (3) thematic coding, object recognition and narrative analysis are the most popular analysis methods that are often conducted manually; (4) computer vision and machine-learning technologies have been increasingly but still infrequently used and are not fit for all purposes; and (5) relatively few papers mention ethics and privacy issues, or apply strategies to address ethical issues. We identify noteworthy research gaps, and opportunities to address limitations and challenges.

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)0.069
metaresearch head score (Gemma)0.269
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.931
Threshold uncertainty score0.363

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0690.269
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.003
Bibliometrics0.0460.033
Science and technology studies0.0020.006
Scholarly communication0.0100.015
Open science0.0020.006
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0050.001

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 head0.469
GPT teacher head0.568
Teacher spread0.099 · 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.

Study designTheoretical or conceptual
DomainMethods
GenreMethods

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

Citations102
Published2021
Admission routes2
Has abstractyes

Explore more

Same venueNew Media & SocietySame topicComputational and Text Analysis MethodsFrench-language works237,207