Computational visualization of customer mood using affective space model approach

• Published in: Frontiers in Artificial Intelligence and Applications
• Main Author: Kamaruddin N.; Handayani D.; Wahab A.
• Format: Conference paper
• Language: English
• Published: IOS Press BV 2017
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85029224955&doi=10.3233%2f978-1-61499-800-6-298&partnerID=40&md5=5d2f6e487b3532c80baeb84d7480a042

Customers' mood information is acquired to facilitate marketers' understanding in order to tailor the marketing strategies for positive outcomes optimization. Mood can be reasonably hypothesized as one of the factor that influences customers' decision in buying the products or services offered. There have been many researchers reporting the correlation between moods and buying decision. However, to date, there is no such method that can exactly quantify the customer's mood. Typically, a questionnaire is given to the participant to gauge their mood on the focused product or services. The drawback from such approach is that participants can fake, exaggerate or suppress their mood resulting to questionable inference. Hence, a new method of data acquisition is needed to be able to visualize the dynamics of the customers' mood for more accurate analysis. In this paper, the customer brain signal is captured using electroencephalogram (EEG) to track and record brain wave patterns in regard to their emotional states. The sequence of emotion is then used to identify their mood. A computational visualization technique is adopted to facilitate understanding of one minute emotion transition that assembling mood. The experimental results show that such approach is feasible and can be extended to study mood in a more comprehensive manner. It is envisaged that this work will be the catalyst for large mood data analysis tool that can help researchers in the near future to look at mood and buying decision for the improvement of comprehensive customer understanding in a more accurate manner. © 2017 The authors and IOS Press. All rights reserved.