Smart wearables, equipped with sensors monitoring physiological parameters, are becoming an integral part of our life. In this work, we investigate the possibility of utilizing such wearables to recognize emotions in the wild. In most reviewed papers, the authors apply a similar procedure consisting of participant recruitment, stimuli preparation and annotation, signal collection and processing, self-assessment, and machine learning model learning and validation. Besides, we identified seven emotion recognition scenarios and analyzed the transition from psychological models to machine learning tasks.

The continuous interest in the social network area contributes to the fast development of this field. The new possibilities of obtaining and storing data facilitate deeper analysis of the entire network, extracted social groups and single individuals as well. One of the most interesting research topic is the dynamics of social groups which means analysis of group evolution over time. Having appropriate knowledge and methods for dynamic analysis, one may attempt to predict the future of the group, and then manage it properly in order to achieve or change this predicted future according to specific needs. Such ability would be a powerful tool in the hands of human resource managers, personnel recruitment, marketing, etc. The social group evolution consists of individual events and seven types of such changes have been identified in the paper: continuing, shrinking, growing, splitting, merging, dissolving and forming. To enable the analysis of group evolution a change indicator—inclusion measure was proposed. It has been used in a new method for exploring the evolution of social groups, called Group Evolution Discovery (GED). The experimental results of its use together with the comparison to two well-known algorithms in terms of accuracy, execution time, flexibility and ease of implementation are also described in the paper.

The Emognition dataset is dedicated to testing methods for emotion recognition (ER) from physiological responses and facial expressions. We collected data from 43 participants who watched short film clips eliciting nine discrete emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, and sadness. Three wearables were used to record physiological data: EEG, BVP (2x), HR, EDA, SKT, ACC (3x), and GYRO (2x); in parallel with the upper-body videos. After each film clip, participants completed two types of self-reports: (1) related to nine discrete emotions and (2) three affective dimensions: valence, arousal, and motivation. The obtained data facilitates various ER approaches, e.g., multimodal ER, EEG- vs. cardiovascular-based ER, discrete to dimensional representation transitions. The technical validation indicated that watching film clips elicited the targeted emotions. It also supported signals’ high quality.

Bringing emotion recognition (ER) out of the controlled laboratory setup into everyday life can enable applications targeted at a broader population, e.g., helping people with psychological disorders, assisting kids with autism, monitoring the elderly, and general improvement of well-being. This work reviews progress in sensors and machine learning methods and techniques that have made it possible to move ER from the lab to the field in recent years. In particular, the commercially available sensors collecting physiological data, signal processing techniques, and deep learning architectures used to predict emotions are discussed. A survey on existing systems for recognizing emotions in real-life scenarios—their possibilities, limitations, and identified problems—is also provided. The review is concluded with a debate on what challenges need to be overcome in the domain in the near future.

To further extend the applicability of wearable sensors in various domains such as mobile health systems and the automotive industry, new methods for accurately extracting subtle physiological information from these wearable sensors are required. However, the extraction of valuable information from physiological signals is still challenging—smartphones can count steps and compute heart rate, but they cannot recognize emotions and related affective states. This study analyzes the possibility of using end-to-end multimodal deep learning (DL) methods for affect recognition. Ten end-to-end DL architectures are compared on four different datasets with diverse raw physiological signals used for affect recognition, including emotional and stress states. The DL architectures specialized for time-series classification were enhanced to simultaneously facilitate learning from multiple sensors, each having their own sampling frequency. To enable fair comparison among the different DL architectures, Bayesian optimization was used for hyperparameter tuning. The experimental results showed that the performance of the models depends on the intensity of the physiological response induced by the affective stimuli, i.e., the DL models recognize stress induced by the Trier Social Stress Test more successfully than they recognize emotional changes induced by watching affective content, e.g., funny videos. Additionally, the results showed that the CNN-based architectures might be more suitable than LSTM-based architectures for affect recognition from physiological sensors.

Wearables like smartwatches or wrist bands equipped with pervasive sensors enable us to monitor our physiological signals. In this study, we address the question whether they can help us to recognize our emotions in our everyday life for ubiquitous computing. Using the systematic literature review, we identified crucial research steps and discussed the main limitations and problems in the domain.