2,644 rated or chosen profiles from 1,322 respondents, in up to 1 tasks of 2 profiles varying on 2 attributes.
| Description | 1,322 Taiwanese adults (online panel, Jan 2024) saw one pair of hypothetical legislative candidates, a woman and a man, as simulated Facebook posts where the post type (campaign, personal viewpoints, personal lives) varied by group. Outcomes: vote choice between the two and a 0-10 impression rating of each. |
|---|---|
| Reference | Yang, W.-Y. (2026). Uneven echoes: Gender's divergent influence on candidate personalization and voter response in Taiwan. Political Communication, 43(5), 807-827. |
| DOI | 10.1080/10584609.2026.2633335 |
| Licence | CC BY 4.0 |
| Source data | https://doi.org/10.6084/m9.figshare.30928337 |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 1,322 |
|---|---|
| Rows (one per respondent, task and profile) | 2,644 |
| Tasks per respondent (most) | 1 |
| Profiles per task | 2 |
| Attributes | 2 |
| Tasks with no profile chosen | 0 |
| Topic | candidate choice |
|---|---|
| A profile represents | person |
| Country | TW |
| Language shown | zh |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): each pair has one female and one male candidate, and the post type is assigned by five fixed pair types: both Campaign; or Campaign plus Personal Viewpoints or Personal Lives for the man or the woman (never both candidates with a personalized post) |
| Task order | recorded in the deposit |
| Profile position | recorded in the deposit |
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.
Outcomes:
| choice | If the legislative election were held tomorrow, which candidate would you vote for? [choice, forced] |
|---|---|
| rating | After viewing the above Facebook post excerpt, please rate your impression of the legislative candidate on a scale from 0 to 10. 0 means 'Dislike very much,' 10 means 'Like very much.' On a scale from 0 to 10, how favorably do you view <candidate name>? [rating, 0 (Dislike very much) to 10 (Like very much)] |
attr_candidate_genderattr_post_typechoicecov_agecov_education_codecov_gender_codecov_survey_weightidprofileratingtasktrial_group
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 (no account needed with irw 1.4.0 or later) or Python (needs a free Redivis account; the first call opens a browser to sign in):
# R
install.packages("irw")
library(irw)
df <- irw_fetch("yang_2026_candidate_posts", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("yang_2026_candidate_posts", source="conj")
Or in Stata, which reads the same no-account CSV as the button above:
* Stata
net install irw, from("https://raw.githubusercontent.com/itemresponsewarehouse/Stata-pkg/main/")
irw_fetch yang_2026_candidate_posts, clear source(conj)
@article{Yang_2026, title={Uneven Echoes: Gender’s Divergent Influence on Candidate Personalization and Voter Response in Taiwan}, volume={43}, ISSN={1091-7675}, url={http://dx.doi.org/10.1080/10584609.2026.2633335}, DOI={10.1080/10584609.2026.2633335}, number={5}, journal={Political Communication}, publisher={Informa UK Limited}, author={Yang, Wan-Ying}, year={2026}, month=Feb, pages={807–827} }
| IRW version | v744 |
|---|---|
| Redivis dataset | irw_conjoint_2 v4.0 |
| Redivis dataset DOI | 10.57761/npz5-mq61 |
| Manifest pin for this IRW version | v4.0 |
| Metadata source | irw_meta v78.0 |