AFFECTIVE DISCOURSE ANALYSIS AND SOCIAL MEDIA: METHODOLOGICAL INNOVATIONS IN THE CROSS-PLATFORM STUDY OF EMOTION AND RACE ON TWITTER, GAB, AND FACEBOOK
Bibliographic record
Abstract
In the context of the so-called "post-truth" crisis, emotions have resoundingly replaced facts in our fast-moving, affectively-driven internet-based culture. Scholars are challenged to develop innovative methods for studying emotion and affect within studies of social media, and political communications. What is an effective interdisciplinary approach to the study of affect and communications in our rapidly-evolving media ecosystems? While the "affective turn" makes sense in the humanities, disciplines studying elections and populist sentiments traditionally draw upon quantitative and qualitative methods that tend to reduce and measure emotions as simply negative and positive. Further, political communications scholarship on "affective polarization" tend to define "in-groups" and "out-groups" solely in terms of partisan differences, missing much complexity of social identities and race relations. This three-year, funded research project draws from the politics of emotion to inform an innovative grounded theoretical study of emotional expression related to narratives of racism in social media. draw on Sarah Ahmed's concepts of sticky emotions and affective economies (2004) and Arlie Hochschild's concepts of feeling rules and deep stories (2016). This talk presents methodological innovations and research findings from our cross-platform digital ethnography of social media from Twitter, Gab, and Facebook, and qualitative discourse analysis of 1800 social media posts related to Black Lives Matter and the Capitol Riots. The paper provides a significant contribution to a nascent field of studies by specifically engaging an interdisciplinary theoretical framework that includes affect theory or politics of emotion alongside qualitative research of 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 | 0.032 | 0.037 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.010 | 0.009 |
| Science and technology studies | 0.007 | 0.022 |
| Scholarly communication | 0.013 | 0.013 |
| Open science | 0.003 | 0.013 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 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".