Examining correlation between trust and transparency with explainable artificial intelligence

TL;DR

This paper investigates how explainable AI can enhance human trust by increasing transparency, demonstrated through a Yelp review rating prediction task where explainability significantly boosted trust levels.

Contribution

It provides empirical evidence that explainable AI increases trust in human-AI interactions within the context of review rating prediction.

Findings

Explainable AI significantly increased trust in the task

Transparency correlates with higher human trust levels

Results support using explainability to improve AI acceptance

Abstract

Trust between humans and artificial intelligence(AI) is an issue which has implications in many fields of human computer interaction. The current issue with artificial intelligence is a lack of transparency into its decision making, and literature shows that increasing transparency increases trust. Explainable artificial intelligence has the ability to increase transparency of AI, which could potentially increase trust for humans. This paper attempts to use the task of predicting yelp review star ratings with assistance from an explainable and non explainable artificial intelligence to see if trust is increased with increased transparency. Results show that for these tasks, explainable artificial intelligence provided significant increase in trust as a measure of influence.