Pilot Study to Design a Chatbot Intervention to Ameliorate Disparities in Breast Cancer Screening

What the dataset is about: this data set includes survey responses for a factorial experiment testing trust and engagement with respect to different chatbot personas for breast cancer screening outreach. There were 4 different versions of chatbot personas (varying on communication style and messenger) and 1 control arm.

When the data were collected: participants were recruited via online survey platforms and completed the survey between August and September 2022.

How many participants provided data: 496

ClinicalTrials.gov ID NCT05472064

What data are included:

Variables:
Response ID
Time Started
Date Submitted
Status
Language
Country
State/Region
Region
Age
Time spent (on multiple pages)
Branching (which arm randomized to)
Outcome measures (see table below)

Outcome Measures
Outcome Measure Measure description
Primary Outcomes
Trust - The human-computer trust scale assesses user trust, which is based on similar constructs of trust (benevolence, competence, reciprocity, perceived risk). 7 of the 12 items were selected which use a 5-point Likert scale from 'Strongly disagree' to 'Strongly agree'.
Intention to Use - This measure assesses likelihood to use this system to schedule a mammogram in the future, and is scored on a 5-point Likert scale from 'Very unlikely' to 'Very likely'.

Secondary Outcomes
Engagement - This measure consists of 4 semantic differential scales assessing traits (important, interesting, relevant, warm) on a 7-point scale.
Directness - This measure consists of 7 semantic differential scales assessing traits (direct, friendly, caring, straightforward, demanding, respectful, polite) on a 7-point scale.
Expertness and Homophily - These 4 items measure the perceived expertise and attitude of the system on a 5-point Likert scale from 'Strongly disagree' to 'Strongly agree'.
Self-brand connection - This measure consists of 3 items to assess self-brand connection on a 5-point Likert scale from 'Strongly disagree' to 'Strongly agree'.