Home // ICIW 2019, The Fourteenth International Conference on Internet and Web Applications and Services // View article

Facial Recognition and Emotion Detection System for Dynamic Advertisement Allocation

Authors:
Frank Yeong-Sung Lin
Evana Szu-Han Fang
Chiu-Han Hsiao

Keywords: dynamic advertisement; facial recognition; emotion detection; audience targeting; decision tree.

Abstract:
Advertisements represent a persuasive method of communication for convincing people to change their thoughts or attitudes. Conventional advertisements do not always provide optimal marketing effectiveness because the advertisements are presented uniformly to viewers. To overcome the limitations of traditional methods in advertising research, a dynamic advertisement model is proposed in this paper, and facial expression detection is applied to real-time measurement during media exposure. This is a novel model to recognize viewers’ facial expression for emotion regulation and then adjust the decision of content sequence according to their emotions. A decision tree algorithm is used, and each demographic measurement results from a few scenarios. The decision is determined through bottom-up branch searching. Based on the study results, personalized advertising and audience targeting with accurate facial expression analysis can allow marketing and advertising researchers to better understand viewers’ emotional valence and behavior and to employ mathematical formulation for establishing the optimal advertising approach.

Pages: 7 to 12

Copyright: Copyright (c) IARIA, 2019

Publication date: July 28, 2019

Published in: conference

ISSN: 2308-3972

ISBN: 978-1-61208-728-3

Location: Nice, France

Dates: from July 28, 2019 to August 2, 2019