7,837 rated or chosen profiles from 1,985 respondents, in up to 4 tasks of 1 profile varying on 4 attributes.
| Description | Danish citizens (n = 1,985 with answers) each rated four fictitious social-media comments (criticism, insult, threat, sexism) addressed to a fictitious politician randomized on name, comment text, channel and party; ratings: abusive, politicians should tolerate it, would report it (1-7). |
|---|---|
| Reference | Petersen, N. B. G., Pedersen, R. T., & Thau, M. (2025). Citizens' perceptions of online abuse directed at politicians: Evidence from a survey experiment. European Journal of Political Research, 64(2), 790-809. |
| DOI | 10.1111/1475-6765.12724 |
| Licence | CC0 1.0 |
| Source data | https://doi.org/10.7910/DVN/LIXDR1 |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 1,985 |
|---|---|
| Rows (one per respondent, task and profile) | 7,837 |
| Tasks per respondent (most) | 4 |
| Profiles per task | 1 |
| Attributes | 4 |
| Topic | political communication |
|---|---|
| A profile represents | message |
| Country | DK |
| Language shown | da |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): The comment type is fixed by task position (task 1 comments 1-5, task 2 comments 6-10, task 3 comments 11-15, task 4 comments 16-20) and a respondent's four comments are distinct; names are drawn with replacement. Message shares are near-equal within type; party shares are unequal (Social Democrats about 17% vs about 5.5% for the smallest). |
| Task order | inferred from row order |
| Profile position | inferred from row order |
Because the attribute levels were not randomized independently, an estimator has to account for the restriction; a plain difference in means across levels can mislead. Task order or profile position was rebuilt from row order; analyses of position or task order should leave it out.
Outcomes:
| rating_abusive | The comments is abusive (variable label) [rating, 1 (unknown) to 7 (unknown)] |
|---|---|
| rating_report | I would report this message (variable label; 'to [Twitter/Facebook]' in the authors' figure code) [rating, 1 (unknown) to 7 (unknown)] |
| rating_tolerate | Politicians should be able to tolerate comments like this (variable label) [rating, 1 (unknown) to 7 (unknown)] |
attr_channelattr_messageattr_nameattr_partycov_agecov_gendercov_left_rightcov_party_idcov_political_interestidprofilerating_abusiverating_reportrating_toleratetasktrial_split_exposure_neg
The layout (one row per respondent, task and profile; choice/rating outcomes; attr_ columns holding each attribute level as displayed) is defined in the IRW conjoint standard. What the outcomes asked is under Design above.
Or load it directly in R or Python (both need a free Redivis account; the first call opens a browser to sign in):
# R
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("petersen_2025_online_abuse", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("petersen_2025_online_abuse", source="conj")
@article{Petersen_2025, title={Citizens’ perceptions of online abuse directed at politicians: Evidence from a survey experiment}, volume={64}, ISSN={1475-6765}, url={http://dx.doi.org/10.1111/1475-6765.12724}, DOI={10.1111/1475-6765.12724}, number={2}, journal={European Journal of Political Research}, publisher={Cambridge University Press (CUP)}, author={Petersen, NIELS BJØRN GRUND and Pedersen, RASMUS TUE and Thau, Mads}, year={2025}, month=May, pages={790–809} }
| IRW version | v584 |
|---|---|
| Redivis dataset | irw_conjoint_2 v1.4 |
| Redivis dataset DOI | 10.57761/hk97-wv30 |
| Manifest pin for this IRW version | v1.4 |
| Metadata source | irw_meta v44.0 |