Emotional Connection with an AI Companion
Exploring how players might feel connected to an AI companion in a narrative game.
Role: Lead User Researcher
Duration: 5 weeks
Method: Playtest, Survey
Tools: Unreal Engine, Microsoft Forms, JASP
Context & Research Goal
The game, Barton, includes an AI companion designed to accompany the player and support them in escaping the planet.
My study’s goal was to see if there was a relationship between the player’s word count when conversing with Barton and their emotional connection with the AI companion.
“Connection Value”
The survey provided included a variety of Likert scale and yes/no questions
I coded this data into a singular quantitative value
Some questions contributed more than others, depending on how directly the question asks about the participant’s views of Barton
The final product is the participant’s connection with Barton, representing a number scaling from 0-30 (0 being no connection, 30 being the highest possible connection)
Scoping
Defined “Connection Value”, reviewed literature on emotional connection.
Playtesting
Eight participants (Ages 18-30). Thirty-minute sessions with word count gathered.
With a p-value under 0.05, the Total Word Count may be an accurate predictor of Connection Value
Survey
Post-session emotional self-report questionnaire.
Key Findings
Analysis
Count words during casual talk, code survey data into “Connection Value”, input both measures into JASP.
Participants with a higher word count with Barton felt emotionally closer to the AI companion
Reflection
The biggest challenge was coding a player’s connection with an AI through a survey. In future studies, I’d incorporate a tool in the game to store all of the participant’s conversations, along with Barton’s responses, to more accurately understand the context of these conversations.
Background
This assignment was done as part of a Psychology course utilizing the JASP program and data from an excel file.
The Influence of Kittens
Objectives
This study was looking to find a relationship between specific kitten photos shown to participants and the cuteness level of their adult counterparts.
Outcome
Through my analysis, I found little evidence showing that being shown a kitten photo prior to showing their adult photo effects the participant’s view of that cat’s cuteness.
Background
This was done as part of a User Research assignment utilizing the game Barton, a first person 3D puzzle/narrative game where you are a pilot seeking to get off of the planet with the help of an AI companion, Barton.
Level Design Playtest
Objectives
The goal of this study was to work alongside other researchers to contribute to one large study, each of us doing a different aspect of the game Barton itself. I was seeking to find how well Barton retained information from the player and listened to the player’s directions when prompted.
Outcome
Barton, at the time, was having trouble retaining information the player was giving them. This did have to do with the LLM’s limitations, which was further improved so Barton would retain information better and wouldn’t make up information that didn’t exist in the context of the game setting.