Evaluating Human and Machine Confidence in Phishing Email Detection: A Comparative Study

TL;DR

This study compares human and machine confidence in detecting phishing emails, revealing that while machines are accurate, humans show more consistent confidence and linguistic cues, guiding better human-AI collaboration.

Contribution

It provides a comparative analysis of human and machine confidence levels in phishing detection, highlighting the importance of interpretability and human factors in AI system design.

Findings

Machine models achieve good accuracy but have variable confidence levels.

Humans use diverse linguistic cues and maintain consistent confidence.

Age affects human detection performance more than language proficiency.

Abstract

Identifying deceptive content like phishing emails demands sophisticated cognitive processes that combine pattern recognition, confidence assessment, and contextual analysis. This research examines how human cognition and machine learning models work together to distinguish phishing emails from legitimate ones. We employed three interpretable algorithms Logistic Regression, Decision Trees, and Random Forests training them on both TF-IDF features and semantic embeddings, then compared their predictions against human evaluations that captured confidence ratings and linguistic observations. Our results show that machine learning models provide good accuracy rates, but their confidence levels vary significantly. Human evaluators, on the other hand, use a greater variety of language signs and retain more consistent confidence. We also found that while language proficiency has minimal effect on detection performance, aging does. These findings offer helpful direction for creating transparent AI systems that complement human cognitive functions, ultimately improving human-AI cooperation in challenging content analysis tasks.