Counterfactual assessment of social media interventions by separating exposure from engagement
Abstract
Social media interventions are usually evaluated in individual-level experiments, which are costly to scale and often miss collective effects. We propose the Exposure--Engagement model, whose parameters separately control what social media users are exposed to (recommendation) and how they engage (behaviour). After fitting it to the Italian Twitter debate (2018--2022), we validate it at individual and collective levels. We simulate behavioural interventions (prebunking and accuracy prompts), calibrated on effect sizes, and a recommender-system intervention (chronological feed), comparing effects on engagement, attention diversity, and segregation. All three reduce engagement. Behavioural interventions slightly reduce diversity, leaving segregation unchanged, whereas the chronological feed increases diversity and reduces segregation. For these interventions, changing recommendation does more for the debate's structure than changing behaviour. We design a recommender-system intervention that increases engagement and diversity while reducing segregation, although with about a tenth of the chronological feed's gains, showing the framework's potential for pro-social intervention design.
Related
- Impact of phantom design on fetal radiation exposure assessment in pregnant women undergoing head and neck 6MV photon radiotherapy
- Distinguishing and separating in-plane hall responses
- Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions
- Distributional Counterfactual Dependence in the Special Sciences
- Separating energy scales in hadron scattering
BibTeX
@misc{pisani2026counterfactual,
title = {{Counterfactual assessment of social media interventions by separating exposure from engagement}},
author = {Tommaso Pisani and Pietro Gravino and Giulio Prevedello},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37864},
eprint = {2610.37864},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37864},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Counterfactual assessment of social media interventions by separating exposure from engagement
AU - Tommaso Pisani
AU - Pietro Gravino
AU - Giulio Prevedello
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.37864
UR - https://arxiv.org/abs/2610.37864
AB - Social media interventions are usually evaluated in individual-level experiments, which are costly to scale and often miss collective effects. We propose the Exposure--Engagement model, whose parameters separately control what social media users are exposed to (recommendation) and how they engage (behaviour). After fitting it to the Italian Twitter debate (2018--2022), we validate it at individual and collective levels. We simulate behavioural interventions (prebunking and accuracy prompts), calibrated on effect sizes, and a recommender-system intervention (chronological feed), comparing effects on engagement, attention diversity, and segregation. All three reduce engagement. Behavioural interventions slightly reduce diversity, leaving segregation unchanged, whereas the chronological feed increases diversity and reduces segregation. For these interventions, changing recommendation does more for the debate's structure than changing behaviour. We design a recommender-system intervention that increases engagement and diversity while reducing segregation, although with about a tenth of the chronological feed's gains, showing the framework's potential for pro-social intervention design.
ER -