Virtual Polarization: study of the dynamics of politically polarized scenarios on social networking sites
Bibliographic record
Abstract
The political discourse in different countries shows distinct levels of polarization, which tend to be stronger in social networking sites, given the ease of connection and engagement with likeminded individuals. One way to reduce polarization would be through a balanced distribution of information showing distinct sides of the same reality among individuals with opposing political views. This study investigates whether this applies in the context of national elections in Brazil and Canada. Political tweets were collected before and after the votes in each scenario, on which the polarization dynamics were analyzed through retweet networks separated weekly. Over these networks, nodes able to distribute information among users with divergent political orientations, called “bubble poppers”, were identified. A new centrality metric called “bubble popper” was proposed and applied for this task – a fundamental metric for this study. Then, the degree to which users, polarized or not, were involved with content shared by bubble poppers, its source (domain), and its theme (topic) was analyzed, considering their political orientation and from who retweeted. As a result, it was identified that users with the highest value for the bubble popper metric were from accounts representing news media with neutral political orientation. While these accounts disseminate information that evenly reaches groups with distinct political orientations, users tend to engage considerably more with content that aligns with their political view, regardless of topic. This same phenomenon was observed in the Brazilian and Canadian political situations, despite having different levels of polarization. This result shows that efforts made by neutral news media to cover different political views in a balanced way may not contribute to reducing the polarization in social networking sites.
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 | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".