Assessing the Effectiveness of Automatic Facial Action Unit Coding In Consumer Marketing Research

Author(s)

Sam TorlayFollow

School Name

South Carolina Governor's School for Science & Mathematics

Grade Level

12th Grade

Presentation Topic

Consumer Science

Presentation Type

Mentored

Abstract

Recently, new technology in the field of facial tracking has been developed called the Automated Facial Action Coding System. This technology can assign a numeric value to the specific emotions someone is experiencing at any moment in time during a recording. The main purpose of this study is to assess how useful this new technology could be for consumer marketing research. Currently, eye-tracking software is being successfully used in marketing studies, and this study is checking if Facial Coding software can be used in much the same way. The experiment consisted of 30 participants interacting with simple packages with different adhesive designs. They were recorded, and the recordings analysed by Imotions facial tracking software to determine the emotional response to the various designs. This emotion data can then be compared statistically to come to a conclusion on design differences. Data is also being collected from self-reports in the post-survey, which was compared to the Imotions data graphically. The results of the study are inconclusive, as there was an extremely large amount of variation in the data, specifically the software results. Additionally, there was little correlation between what the participants self-reported, and what was picked up by the Imotions software. However, the software did successfully measure large mean differences in the emotions of participants. Future studies with larger sample sizes would be necessary to come to a consensus on the usefulness of this technology.

Location

Furman Hall 118

Start Date

3-28-2020 11:45 AM

Presentation Format

Oral Only

Group Project

No

COinS
 
Mar 28th, 11:45 AM

Assessing the Effectiveness of Automatic Facial Action Unit Coding In Consumer Marketing Research

Furman Hall 118

Recently, new technology in the field of facial tracking has been developed called the Automated Facial Action Coding System. This technology can assign a numeric value to the specific emotions someone is experiencing at any moment in time during a recording. The main purpose of this study is to assess how useful this new technology could be for consumer marketing research. Currently, eye-tracking software is being successfully used in marketing studies, and this study is checking if Facial Coding software can be used in much the same way. The experiment consisted of 30 participants interacting with simple packages with different adhesive designs. They were recorded, and the recordings analysed by Imotions facial tracking software to determine the emotional response to the various designs. This emotion data can then be compared statistically to come to a conclusion on design differences. Data is also being collected from self-reports in the post-survey, which was compared to the Imotions data graphically. The results of the study are inconclusive, as there was an extremely large amount of variation in the data, specifically the software results. Additionally, there was little correlation between what the participants self-reported, and what was picked up by the Imotions software. However, the software did successfully measure large mean differences in the emotions of participants. Future studies with larger sample sizes would be necessary to come to a consensus on the usefulness of this technology.