Data Sheet 1_A randomized factorial experiment to optimize the design of a culturally tail

A 2 × 2 factorial experiment data evaluating chatbot persona and communication style effects on trust and intention to use for breast cancer screening scheduling. The dataset, authored by Raina Langevin and last updated in April 2026, contains results from a mixed-methods analysis comparing a Black woman persona presented as a doctor or survivor with direct or polite communication styles against a control.

Use Cases

• Analyzing the impact of chatbot persona (doctor vs. survivor) on user trust based on the experimental design described.
• Evaluating the effect of communication style (direct vs. polite) on intention to use for scheduling health services.
• Studying qualitative perceptions of cultural tailoring and potential stereotyping in AI persona development.
• Comparing quantitative preference scores for different experimental conditions (e.g., doctor-polite) against a control.

Strengths

• Data originates from a registered clinical trial (NCT05472064), suggesting a structured methodology.
• Includes both quantitative and qualitative feedback from participants, providing mixed-methods insights.
• Released under a CC-BY-4.0 license, permitting broad reuse and adaptation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale modeling.
• The 1.0 MB file size suggests a small dataset, potentially limiting statistical power for some analyses.

Provenance

Source

figshare

Collection Method

Randomized factorial experiment with mixed-methods analysis.

Time Range

Study protocol registered on ClinicalTrials.gov (NCT05472064); specific data collection period not stated.

Freshness

Last updated 2026-04-22 05:46:06; freshness should be verified.

Geography

Geographic coverage of participants is not specified in the provided metadata.