AI-based User Emotion Recognition from Interaction Data

Nowadays, it is possible to recognize user emotions with the help of different data sources like facial expressions or user interactions. The collection of Keystroke, Mouse and Touchscreen (KMT) interaction data can be done unobtrusively as an additional data source. In order to create algorithms that detect emotions exclusively on KMT data, we first need datasets containing KMT and emotional data. Data is a fundamental part of all data-driven and artificial intelligence-related research. Independent verification of published results is crucial for ensuring research quality and promoting further advancements. However, reproducibility in data-focused research is a growing concern across disciplines. Our research aims to improve the reproducibility of interaction-based emotion recognition research.

We focus on improving the data sharing practices in the area of interaction based emotion recognition. Furthermore, we want to strengthen the publications which shared their data, by reproducing the results. Finally, we want to provide a summary of the state of the art and possible outlooks.