Replication data from a study evaluating the persuasive effects of emotional campaign advertisements. The dataset likely contains results from 29 weeks of experiments during the 2016 U.S. presidential campaign, where 48 authentic ads and a placebo were randomly assigned to approximately 28,000 subjects. The study was authored by Alexander Coppock and is hosted by Harvard Dataverse.
Use Cases
- Analyzing the relationship between emotional reactions and candidate favorability based on experimental results.
- Studying partisan differences in emotional responses to campaign advertisements.
- Investigating the predictive power of self-reported emotions on vote intention and policy preferences.
- Replicating experimental findings on advertising effectiveness in polarized elections.
Strengths
- Experiments conducted over 29 weeks during a major election cycle.
- Approximately 28,000 subjects participated in the randomized ad assignments.
- Analysis of 48 authentic campaign ads tested in real time.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Data may reflect temporal bias inherent to the 2016 U.S. election context.
Provenance
- Source
- Harvard Dataverse
- Collection Method
- Randomized experiments conducted during the 2016 U.S. presidential campaign.
- Time Range
- 2016 U.S. presidential campaign period (29 weeks of experiments).
- Freshness
- Last updated 2026-04-14 01:39:02; freshness should be verified.
- Geography
- United States