Using EEG emotion models in viewer experience design: An exploratory study

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

ACM International Conference Proceeding Series

Volume

Part F137694

First Page

82

Last Page

88

Publication Date

3-23-2018

Abstract

© 2018 Association for Computing Machinery. TV Commercials are often considered to be noise that viewers see in between their favorite shows. These have been used for mostly commercial and advertising purposes. Such practice has been an established one for decades. Most advertising researchers have always relied on traditional means and techniques in measuring viewer experiences and understanding conversion rates from these TV Commercials. In this work-in-progress, we present our preliminary findings from an exploratory study on understanding consumer behaviors and emotions especially when watching TV Commercials. Target consumers for a specific commercial product underwent one-on-one semi-structured interviews and from viewing sessions where their EEG data were collected using the 5-channel EMOTIV Insight headset. To triangulate the emotion modeling phase, external observers referred to as coders annotated their emotions with the aid of emotion recognition via facial recognition. Initial Analysis of the interviews along with the early version of the model revealed several interesting points on visual and audio elements that triggered viewer valence. The collection of EEG data was also able to uncover a few insights that aided in the design of a better viewing experience for the target consumers. We intend to expand the findings in the future work to build a model from a bigger data and user base along with a wider array of emotions to choose from. Also, we intend to employ more advanced experiment designs to determine if we can directly correlate viewer experiences into actual product and commercial conversion.

html

Digitial Object Identifier (DOI)

10.1145/3205946.3205958

Upload File

wf_yes

This document is currently not available here.

Share

COinS