Development and Validation of an Experimental Protocol for Facial Emotion Recognition

Emotions are integral to human behavior and are influenced by external stimuli, such as visual cues, which can introduce biases. Accurate measurement of emotional responses is crucial, particularly in fields like bioengineering and neuroscience. This article explores Facial Emotion Recognition (FER) as a tool to quantify emotional reactions objectively. The study includes two phases: the development and validation of an Online Task (to present visual stimuli from the OASIS dataset and ask participants to classify their emotions via a quiz) and the creation of an Offline FER Algorithm to classify the emotion based on facial expressions. Our results highlight the importance of using large datasets of images with strong and verified emotional responses to calibrate FER algorithms. Future works, focusing on integrating the online task with the FER algorithm, would allow for a real-time emotion monitoring in various applications, such as healthcare, education, privacy, law, and human-computer interaction.