Emotions are contagious, yet empirical knowledge on how they spread in groups is limited. A better understanding could help optimize social environments and benefit models predicting group affect. This study investigates how gaze attention affects emotional convergence in group video calls. Building on previous research that identified emotion contagion in competitive teams, we incorporated eye-tracking to analyse gaze direction and its relation to emotional responses. Results indicate the expressions of participants converged towards (1) the average emotion in the virtual room when looking at opponents, but not team members, and (2) the specific emotion of the individual they looked at, regardless of team affiliation. No link was found between personality and emotional convergence. We conclude that gaze attention predicts emotional convergence in group video calls. Further study is needed to establish a causal relationship and assess generalizability. We discuss the implications for video conferencing and simulating emotion contagion in groups.

In an era of rapid technological advancements, computer systems play a crucial role in early Violence Detection (VD) and localization, which is critical for timely human intervention. However, existing VD methods often fall short, lacking applicability to surveillance data, and failing to address the localization and social dimension of violent events. To address these shortcomings, we propose a novel approach to integrate subgroups into VD. Our method recognizes and tracks multiple subgroups across frames, providing an additional layer of information in VD. This enables the system to not only detect violence at video-level, but also to identify the groups involved. This adaptable add-on module can enhance the applicability of existing models and algorithms. Through extensive experiments on the SCFD and RWF-2000 surveillance datasets, we find that our approach improves social awareness in real-time VD by localizing the people involved in an act of violence. The system offers a small performance boost on the SCFD dataset and maintains performance on RWF-2000, reaching 91.3% and 87.2% accuracy respectively, demonstrating its practical utility while performing close to state-of-the-art methods. Furthermore, our efficient method generalizes well to unseen datasets, marking a promising advance in early VD.

Applications of emotionally expressive virtual humans in society are growing, often in the form of AI-driven autonomous agents. In this study however, we explore an application where virtual humans act as intermediaries in human-to-human communication, a type of application that has received significant attention but is not widely available yet. Specifically, participants communicate in a video call setting, where, instead of webcam footage, they observe others via human-like avatars. The avatars mimic in real-time the facial expressions of the person they represent. By contrasting this with a control condition where avatars do not mimic expressions, the study aims to test whether emotional expressions via avatars are contagious and drive collective emotion in a similar way as previously found for regular video calls. The recorded facial expressions of the participants are annotated manually and automatically, while the attention towards others in the group is recorded by tracking the gaze of the participants. We hypothesised emotion contagion would drive emotional convergence at the group level and in gaze pairs. The results show that the opposite may have taken place. Looking at the avatars of others was related to a decrease in similarity of facial expressions and emotional content of those expressions, compared to before the gaze. This was found both with and without mimicking avatars, yet more negative expressions were present in the control condition compared to the avatars that mimicked expressions. We discuss potential explanations and implications of these findings and make recommendations for future designs.

In recent years, many agent-based models of human groups have implemented a mechanism of emotion contagion, yet empirical validation is lagging behind. The aim of the present paper is to validate an agent-based model of emotion contagion at the level of group emotion, by comparing simulations against the emotional development of real people in small groups. To study the effect of emotion contagion, the participants interacted via a video call, where they were virtually placed in different social environments while they played a quiz. This allowed the exchange of emotion among all, some or none of the participants. The patterns of emotional development in the empirical results supported our hypotheses based on literature of emotion contagion and social norms. Further, the simulations with the complete model resembled many of these patterns. When emotion contagion was disabled in the model, the resemblance decreased. These results give a first indication that emotion contagion occurs in groups that meet via video calls, and can in-part be predicted by the proposed model of emotion contagion. Yet, further study with a larger and more diverse empirical sample is needed, as well as comparisons across contagion mechanisms, to draw stronger conclusions and ultimately justify societal application.

Abstract Emotions are known to spread among people, a process known as emotion contagion. Both positive and negative emotions are believed to be contagious, but the mass spread of negative emotions has attracted the most attention due to its danger to society. The use of agent-based techniques to simulate emotion contagion in crowds has grown over the last decade and a range of contagion mechanisms and applications have been considered. With this review we aim to give a comprehensive overview of agent-based methods to implement emotion contagion in crowd simulations. We took a systematic approach and collected studies from Web of Science, Scopus, IEEE and ACM that propose agent-based models that include a process of emotion contagion in crowds. We classify the models in three categories based on the mechanism of emotion contagion and analyse the contagion mechanism, application and findings of the studies. Additionally, a broad overview is given of other agent characteristics that are commonly considered in the models. We conclude that there are fundamental theoretical differences among the mechanisms of emotion contagion that reflect a difference in view on the contagion process and its application, although findings from comparative studies are inconclusive. Further, while large theoretical progress has been made in recent years, empirical evaluation of the proposed models is lagging behind due to the complexity of reliably measuring emotions and context in large groups. We make several suggestions on a way forward regarding validation to eventually justify the application of models of emotion contagion in society.

This article aims to summarize and describe research on the topic of automatic group emotion recognition. In recent years, the topic of emotion analysis of groups or crowds has gained interest, with studies performing emotion detection in different contexts, using different datasets and modalities (such as images, video, audio, social media messages), and taking different approaches. Articles are included after an innovative search method, including Dense Query Extraction and automatic cross-referencing. Discussed are the types of groups and emotion models considered in automatic emotion recognition research, common datasets for all modalities, general approaches taken, and reported performances. These performances are discussed, followed by an analysis of the application possibilities of the discussed methods. To ensure clear, replicable, and comparable studies, we suggest research should test on multiple, common datasets and report on multiple metrics, when possible. Implementation details and code should be made available where possible. An area of interest for future work is to build systems with more real-world application possibilities, coping with changing group sizes, different emotional subgroups, and changing emotions over time, while having a higher robustness and working with datasets with reduced biases.

Both social group detection and group emotion recognition in images are growing fields of interest, but never before have they been combined. In this work we aim to detect emotional subgroups in images, which can be of great importance for crowd surveillance or event analysis. To this end, human annotators are instructed to label a set of 171 images, and their recognition strategies are analysed. Three main strategies for labeling images are identified, with each strategy assigning either 1) more weight to emotions (emotion-based fusion), 2) more weight to spatial structures (group-based fusion), or 3) equal weight to both (summation strategy). Based on these strategies, algorithms are developed to automatically recognize emotional subgroups. In particular, K-means and hierarchical clustering are used with location and emotion features derived from a fine-tuned VGG network. Additionally, we experiment with face size and gaze direction as extra input features. The best performance comes from hierarchical clustering with emotion, location and gaze direction as input.

This article is part of a project that explores the potential of chatbots for providing online emotional support to humans tailored to stressors. Based on a number of empirical studies, we have developed a socially interactive agent able to have simple dialogues with stressed humans seeking for emotional support. In the current article, we address the question to what extent this chatbot is effective in helping users cope with stressful situations. To this end, we present a study in which participants were asked to interact with our proposed chatbot for three days. Participants are distributed over the following three conditions—namely: 1) receiving support from the chatbot, knowing the support is computer-generated; 2) receiving support from the chatbot, while believing the support is human-generated; 3) not receiving any support. During the three days, participants’ self-reported stress levels are measured on a daily basis before and after each interaction. Results indicate that the best results are obtained in the ‘human’ condition, while the worst results are obtained in the “computer” condition. These findings lead us to conclude that the presumed sender of a stress support message (i.e., a human or a computer) might be more important than the content of the message.

In recent years, simulation techniques have been applied to investigate the spatiotemporal dynamics of crime. Researchers have instantiated mobile offenders in agent-based simulations for theory testing, experimenting with crime prevention strategies, and exploring crime prediction techniques, despite facing challenges due to the complex dynamics of crime and the lack of detailed information about offender mobility. This paper presents a simulation model to explore offender mobility, focusing on the interplay between the agent's awareness space and activity nodes. The simulation generates patterns of individual mobility aiming to cumulatively match crime patterns. To instantiate a realistic urban environment, we use open data to simulate the urban structure, location-based social networks data to represent activity nodes as a proxy for human activity, and taxi trip data as a proxy for human movement between regions of the city. We analyze and systematically compare 35 different mobility strategies and demonstrate the benefits of using large-scale human activity data to simulate offender mobility. The strategies combining taxi trip data or historic crime data with popular activity nodes perform best compared to other strategies, especially for robbery. Our approach provides a basis for building agent-based crime simulations that infer offender mobility in urban areas from real-world data.

Artificial Intelligence techniques are increasingly being used to develop smart training applications for professionals in various domains. This paper presents an intelligent training system that enables professionals in the public domain to practice their aggression de-escalation skills. The system is one of the main products of the STRESS project, an interdisciplinary research project involving partners from academia, industry and society. The system makes use of a variety of AI-related techniques, including simulation, virtual agents, sensor fusion, model-based analysis and adaptive support. A preliminary evaluation of the system has been conducted with two groups of potential end users, namely tram conductors and police academy students.

To enhance believability of virtual agents, this paper presents an agent-based modelling approach for decision making, which integrates rational reasoning based on means-end analysis with personal psychological and biological aspects. The agent model developed is a combination of a BDI-model and a utility-based decision model in the context of specific desires and beliefs. The approach is illustrated by addressing the behaviour of violent criminals, thereby creating a model for virtual criminals. Within a number of simulation experiments, the model has been tested in the context of a street robbery scenario. In addition, a user study has been performed, which confirms the fact that the model enhances believability of virtual agents.

Central research questions addressed within Criminology are how the geographical displacement of crime can be understood, explained, and predicted. The process of crime displacement is usually explained by referring to the interaction of three types

Multi-agent organization modeling, norm violation, avoidance In contemporary society not adhering to norms is something which is unwanted. Currently approaches to prevent this from happening are often taken whereby the deviation of a norm is punished and possible repair actions are performed. However, this is a reactive approach and can only happen once the norm has already been violated. This paper presents a proactive approach which allows intervention before the deviation actually occurs. In order to do this, an approach is specified for agents that enforce norms and can influence the input states of agents. This approach includes learning of input/output correlations of these agents by constructing decision trees, and utilizing this decision tree to intervene such that norm violation can be avoided. The approach is evaluated in the domain of Criminology.

Within Criminology, the process of crime displacement is usually explained by referring to the interaction of three types of agents: criminals, passers-by, and guardians. Most existing simulation models of this process are agent-based. However, when the number of agents considered becomes large, population-based simulation has computational advantages over agent-based simulation. This paper presents both an agent-based and a population-based simulation model of crime displacement, and reports a comparative evaluation of the two models. In addition, an approach is put forward to analyse the behaviour of both models by means of formal techniques.