College - Author 1

College of Engineering

Department - Author 1

Industrial and Manufacturing Engineering Department

College - Author 2

College of Engineering

Department - Author 2

Computer Science Department

Advisor

Duha Ali, College of Engineering, Industrial and Manufacturing Engineering; Javier Sanchez, College of Engineering, Computer Science and Software Engineering; Rafael Guerra Silva, Orfalea College of Business

Funding Source

The Sprague Family Foundation

Date

10-2024

Abstract/Summary

This study argues that while AI systems have become increasingly advanced, they still evoke distinct emotional responses compared to human interactions, potentially limiting their effectiveness in emotionally-driven environments. We used the Emotiv Insight brain-computer interface to monitor participants' emotional responses during controlled interactions with both AI systems and other humans. Key emotional metrics, such as arousal, focus, and stress, were recorded in real time, providing a detailed picture of the emotional dynamics at play in each type of interaction. Participants exhibited higher levels of excitement, stress, and focus during interactions with humans compared to AI systems, while other emotions like engagement and pleasure were relatively similar across both interaction types. These findings reveal that AI systems may struggle to evoke the same intensity of emotional responses as human interactions. Understanding these emotional differences is crucial for refining AI systems to foster more emotionally engaging and natural user experiences, contributing to the development of more effective communication tools in human-AI interactions.

Share

COinS
 

URL: https://digitalcommons.calpoly.edu/ceng_surp/54

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.