Race and Ethnicity in Facebook Images and Text: Thematic Analysis
Bibliographic record
Abstract
BACKGROUND: Social media platforms, such as Facebook, provide a dynamic public space where users of various racial and ethnic backgrounds share content related to identity, politics, and other social issues. These platforms allow racially minoritized groups to both challenge racial silencing and express cultural pride. At the same time, they expose users to racism and stereotypes that can negatively affect their mental and physical health through psychosocial stress. Given the rise of multimodal communication, it is essential to study both images and text to fully understand how race and ethnicity are discussed in digital spaces. OBJECTIVE: This exploratory, descriptive study aimed to investigate how people discuss race and ethnicity on Facebook and specifically examine themes related to cultural pride, solidarity, racism, antiracism, and politics using qualitative content analysis of race- and ethnicity-related Facebook posts with images and text. These themes reflect how individuals construct identity, engage with other social identities, and navigate sociopolitical discourse in digital spaces. METHODS: We conducted a qualitative content analysis using a hybrid inductive-deductive approach. A total of 500 multimodal Facebook posts were randomly sampled using CrowdTangle, with 100 posts from each year between 2019 and 2023. Each post included both image and text and contained at least 1 race- or ethnicity-related keyword. Posts were uploaded to GitHub for storage and to Label Studio for coding. An iteratively developed codebook guided the analysis, focusing on representations of race and ethnicity, the continuum of race-related discourse, and topical content. All posts were double coded until an 80% interrater agreement was reached. The remaining discrepancies were resolved through coder consensus to ensure reliability and consistency. Themes were solidified through thematic analysis. RESULTS: Across 500 Facebook posts from 2019 to 2023, nearly one-third lacked clear racial specificity, with 19.8% (99/500) unrelated to race and 11.2% (56/500) mentioning no specific racial or ethnic group. Among the identified groups, Hispanic, multiracial, and immigrant communities were the most frequently referenced. Common themes included US politics, cultural pride, racism and stereotypes, and antiracism. Political content was the most crosscutting theme, while cultural pride and racism-related discourse varied by group. Antiracism posts reflected the national response to racial justice movements. These findings highlight the nuanced and evolving nature of race-related discourse on social media. CONCLUSIONS: It can be complicated to interpret image-based posts because of the subtle ways in which an image may reference race and ethnicity but does not explicitly mention it, or when there is a contradiction in the ideas portrayed in the image versus the text. Decoding this process on Facebook can help researchers boost the positive impacts and reduce the harmful effects of racism on social media.
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 | 0.018 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.009 |
| Science and technology studies | 0.005 | 0.006 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".