Visual Social Media and Big Data. Interpreting Instagram Images Posted on Twitter
Bibliographic record
Abstract
Social media such as Twitter and Instagram are fast, free, and multicast. These attributes make them particularly useful for crisis communication. However, the speed and volume also make them challenging to study. Historically, journalists controlled what/how images represented crises. Large volumes of social media can change the politics of representing disasters. However, methodologically, it is challenging to study visual social media data. Specifically, the process is usually labour-intensive, using human coding of images to discern themes and subjects. For this reason, Studies investigating social media during crises tend to examine text. In addition, application programming interfaces (APIs) for visual social media services such as Instagram and Snapchat are restrictive or even non-existent. Our work uses images posted by Instagram users on Twitter during Hurricane Sandy as a case study. This particular case is unique as it is perhaps the first US disaster where Instagram played a key role in how victims experienced Sandy. It is also the last major US disaster to take place before Instagram images were removed from Twitter feeds. Our sample consists of 11,964 Instagram images embedded into tweets during a twoweek timeline surrounding Hurricane Sandy. We found that the production and consumption of selfies, food/drink, pets, and humorous macro images highlight possible changes in the politics of representing disasters - a potential turn from top-down understandings of disasters to bottom-up, citizen informed views. Ultimately, we argue that image data produced during crises has potential value in helping us understand the social experience of disasters, but studying these types of data presents theoretical and methodological 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 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 | 0.003 | 0.026 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.000 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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.
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".