Social Signal Processing is the research domain aimed at bridging the social intelligence gap between humans and machines. This paper is the first survey of the domain that jointly considers its three major aspects, namely, modeling, analysis, and synthesis of social behavior. Modeling investigates laws and principles underlying social interaction, analysis explores approaches for automatic understanding of social exchanges recorded with different sensors, and synthesis studies techniques for the generation of social behavior via various forms of embodiment. For each of the above aspects, the paper includes an extensive survey of the literature, points to the most important publicly available resources, and outlines the most fundamental challenges ahead.

The automatic monitoring and assessment of the engagement level of learners in distance education may help in understanding problems and providing personalized support during the learning process. This article presents a research aiming to investigate how student engagement level can be assessed from facial behavior and proposes a model based on Long Short-Term Memory (LSTM) networks to predict the level of engagement from facial action units, gaze, and head poses. The dataset used to learn the model is the one of the EmotiW 2019 challenge datasets. In order to test its performance in learning contexts, an experiment, involving students attending an online lecture, was performed. The aim of the study was to compare the self-evaluation of the engagement perceived by the students with the one assessed by the model. During the experiment we collected videos of students behavior and, at the end of each session, we asked students to answer a questionnaire for assessing their perceived engagement. Then, the collected videos were analyzed automatically with a software that implements the model and provides an interface for the visual analysis of the model outcome. Results show that, globally, engagement prediction from students’ facial behavior was weakly correlated to their subjective answers. However, when considering only the emotional dimension of engagement, this correlation is stronger and the analysis of facial action units and head pose (facial movements) are positively correlated with it, while there is an inverse correlation with the gaze, meaning that the more the student’s feels engaged the less are the gaze movements.

Following the Digital Revolution, we are witnessing an increase in the number of manipulated sources of information. For this reason, virtual environments can be a breeding ground for the proliferation of prejudices and stereotypes, resulting from the spread of racial fallacious news, known as ‘racial hoaxes’. Adolescents may be more susceptible due to the tense and complicated relationship between their experience with digital platforms and the development of their relatively limited critical thinking. In this landscape, in order to explore the features of disinformation in adolescence, the research involved 41 Italian adolescents between 13 and 16 years old, balanced by gender and school education. The teenagers took part in the focus group discussions on the topic of online information preferences, fake news and racial hoaxes, which were analyzed by means of content analysis. The answers given by participants show a so-called adolescents’ perception of ‘misinformation invulnerability’ that can influence their credulity in fake news, since they are aware of fake news but they are not so able to recognize or remember it.

Purpose: The purpose of this paper is to explore the “dark nuances” of social media by identifying moral disengagement (MD) mechanisms and hostile emotions in people discussing the hosting of immigrants and examining the relationship between MD mechanisms and hostile emotions expressed online (annoyance, irritation and contempt). Design/methodology/approach: The method was based on a psycho-lexicographical approach that analysed the in vivo real words, adopting a quanti-qualitative point of view. The investigation started from the case of a Facebook post in support of immigrants after a serious shipwreck causing the death of more than 700 would-be migrants. More than 10,000 comments were codified. For the comments against the hosting of such immigrants, the authors followed a codebook aimed at identifying MD mechanisms and hostile emotions. Findings: The main findings show an interplay between different hostile negative emotions and online MD mechanisms. The greater the intensity of hostile emotions, the more the locus of disengagement moves from the unethical individual’s behaviour – for example, offering moral justifications – to the target recipient of such behaviour – for example, blaming or dehumanising. Practical implications: The study could be applicable in designing and developing algorithms and technological tools aimed at preventive interventions to promote moral awareness and emotional regulation in online settings. Social implications: The study may be a useful contribution to understanding unethical orientation by identifying areas where education can intervene in reducing harmful behavioural tendencies. Originality/value: This study takes together expressed hostile emotions and MD mechanisms by means of the analysis of real words in vivo through social media discussions.

During a non-invasive procedure, participants both helped and helped by a confederate with features that create social distance (membership in an ethnic outgroup or another social group). For this purpose, we created a set of virtual scenarios in which the confederate’s ethnicity (white vs. black) and appearance (business man vs. beggar, with casual dress as a control condition) were crossed. The study aimed to explore how the emotional reactions of participants changed according to the confederate’s status signals as well as signals that they belong to the same or a different ethnic group. Participants’ alertness, calmness, and engagement were monitored using electroencephalogram (EEG) during the original virtual reality (VR) video sessions. Participants’ distress and empathy when exposed to helping interactions were self-assessed after the VR video sessions. The results pointed out that, irrespective of whether they helped the confederate or were helped by him/her, white participants showed higher levels of alertness when exposed to helping interactions involving a white beggar or a black businessman, and their emotional calmness and engagement were higher when interacting with a black beggar or a white businessman. The results for self-assessed distress and empathy followed the same tendency, indicating how physiological and self-assessed measures can both contribute to a better understanding of the emotional processes in virtual intergroup helping situations. Based on the presented results, the methodological and practical implications of VR in terms of enhancing self-reflective capacities in intergroup helping processes are discussed.

This paper provides an overview of previous works on the acoustic parameters of charismatic voice and illustrates MASCharP, a scale for measuring the perception of charisma in voice. A study is then presented on the perception of charisma through the temporal and pitch structure of the voices of an Italian and a French politician. Results show some cultural differences in charisma perception and how acoustic features such as pitch (normal, higher, or lower) and types of pauses (short or long) can affect the Proactive-Attractive and Calm-Benevolent dimensions of charisma. The same dimension of charisma can be conveyed by different acoustic correlates of voice by connecting them to the dimension of leader extraversion-introversion.