Abstract
Despite advancements in emotion recognition, the suitability of existing AI models for daily use remains uncertain. Creating more accurate solutions requires amounts of data uncollectible in a laboratory setting, thus forcing researchers to focus on a more information-rich environment – everyday life. However, the constraints of the in-the-field studies are different than those of the in-the-lab ones, which are familiar to most researchers. In this work, we delve into the challenges in designing and conducting a large-scale real-life affective study, employing wearable devices and smartphones for data collection. Among others, we describe in detail the impact of delays on the whole process and related issues, such as using untested features and oversights in the main study. Moreover, we highlight other faced challenges, made decisions, and mistakes, which, we believe, are valuable for researchers aiming to conduct studies in a real-life setting.