Background Hardly Matters: Understanding Personality Attribution in Deep Residual Networks

TL;DR

This study investigates how background information influences deep neural network predictions of perceived personality traits, finding that backgrounds do not improve and may even hinder model performance.

Contribution

The paper clarifies the impact of image backgrounds on personality attribution models, addressing confounds and demonstrating backgrounds do not enhance prediction accuracy.

Findings

Background information does not improve model predictions.

Adding background explicitly decreases model performance.

No evidence found that backgrounds influence personality attribution.

Abstract

Perceived personality traits attributed to an individual do not have to correspond to their actual personality traits and may be determined in part by the context in which one encounters a person. These apparent traits determine, to a large extent, how other people will behave towards them. Deep neural networks are increasingly being used to perform automated personality attribution (e.g., job interviews). It is important that we understand the driving factors behind the predictions, in humans and in deep neural networks. This paper explicitly studies the effect of the image background on apparent personality prediction while addressing two important confounds present in existing literature; overlapping data splits and including facial information in the background. Surprisingly, we found no evidence that background information improves model predictions for apparent personality traits. In fact, when background is explicitly added to the input, a decrease in performance was measured across all models.