Stress Detection Systems Stumble When Users Are Already Stressed
Researchers found that emotion-recognition AI performs significantly worse when analyzing people who have recently experienced stress, a phenomenon called the priming effect. The discovery threatens the reliability of stress-detection systems being deployed in healthcare and workplace wellness programs, forcing developers to rethink how these tools are designed and validated.
Originaltitel: Stress Lingers: Recognizing the Impact of Task Order on Design of Stress and Emotion Detection Systems
<p>This paper examines the significance of the priming effect in designing and developing models for recognizing of affective states. Using a public dataset, often considered a benchmark in automatic stress recognition, the significance of the priming effect is explicated. Two experimental setups confirm the importance of task ordering in this problem. The results demonstrate the statistical significance of the model’s confusion when the subject has previously experienced stress and illustrate the importance for the Affective Computing community to develop methods to mitigate the priming effect where the order of tasks impacts how data should be modelled.</p>