Analysis of user inclination in movie posters based on color bias using transfer learning
Published in Emerging Technologies in Data Mining and Information Security, 2022
Abstract: Visual bias can be described as the phenomenon of showing a preference for a particular visual stimulant based on some inherently unique characteristics possessed by it. This predisposition is quite apparent in everyday life: different people respond differently to the same visual information. The careful utilization of this phenomenon can be extremely utilitarian. This is apparent from the recent widespread acknowledgment of visual bias, and its manipulation to bring about salutary business effects. Today, visual bias utilization can be seen at play in a number of different industries ranging from advertisements to recommendation systems of OTT giants. Despite the fact that the existence of visual bias is now widely accepted, few empirical studies have been conducted to confirm the same. The present article and the ensuing research serve to bridge that gap. In our article, we elucidate the salient points of the research. We conducted using movie posters as a means of estimating and studying the effects of visual bias. We built a Web application to survey and collect user ratings for movie posters belonging to different genres and thus having different visual effects. Based on the user’s input, a bias mapping was done, and the result of which was the genre that the user was most visually partial to. Contingent on that, neural style transformation was applied to movie posters, and the augmented results were presented to the user to rate. By comparing the initial genre-wise ratings to the transformed genre ratings, the extent of visual bias was detected and thus analyzed. Our study not only confirmed the empirical existence of such bias, but the detection methodology outlined here may serve as a visual bias manipulation tool that can utilize real-time machine learning to optimize AdSense and the likes.
Keywords: Visual bias, Neural style transfer, Convolutional neural networks
Recommended Citation: Chadha, H. , Madan, D., Rana, D., & Sharma, N. (2022, September 30). Analysis of User Inclination in Movie Posters Based on Color Bias. Advances in Intelligent Systems and Computing, 303–311. https://doi.org/10.1007/978-981-19-4676-9_25
Collaborators - Deeksha Madan, Deepika Rana, Dr. Neelam Sharma