Recognizing Developers' Emotions while Programming
This addresses the problem of understanding and monitoring emotional states in software developers to potentially improve job performance, though it is incremental as it builds on previous findings.
The study investigated the link between emotions and progress in programming, identifying triggers and coping strategies, and found that developers' emotions can be reliably recognized using only a wristband with electrodermal activity and heart metrics.
Developers experience a wide range of emotions during programming tasks, which may have an impact on job performance. In this paper, we present an empirical study aimed at (i) investigating the link between emotion and progress, (ii) understanding the triggers for developers' emotions and the strategies to deal with negative ones, (iii) identifying the minimal set of non-invasive biometric sensors for emotion recognition during programming task. Results confirm previous findings about the relation between emotions and perceived productivity. Furthermore, we show that developers' emotions can be reliably recognized using only a wristband capturing the electrodermal activity and heart-related metrics.