Search

SPACES

In the Simulation-based Prediction and Analysis of Collective Emotional States (SPACES) project an intelligent system will be developed to help guardians predict and control the emergence of unwanted behaviour in crowds. Nowadays, many hi-tech solutions are already available to monitor crowds, e.g. using infrared cameras and sound detection. Unfortunately, these are both expensive, and (currently) have to be placed at a fixed location. In this project we propose the use of data available via social media which constitutes a cost-effective and flexible solution. The widespread use of social media nowadays provides an interesting new angle on monitoring large crowds. Social media are an interesting source of qualitative information and by analysing this information it should be possible to predict potential behaviour. Information posted on social media is available at low cost and analysing such data is a cost-effective means to get insight in what is exactly going on in a crowd, before, during and after large mass events.

Using this input, SPACES will make a prediction of the development of a scenario in the near future. The main technique for making this prediction is agent-based simulation. Specifically, an agent-based simulation model will be developed that contains knowledge about the intra- and interpersonal dynamics of the (mental) states and actions of individuals in a crowd, such as emotion contagion, and (group) decision making. Based on this model, the system will be able to predict, for example, the emergence of aggressive outbursts, panicking behaviour, or congested areas in parts of a crowd.

The proposed project envisions development and testing of a combination of innovative techniques, including dedicated methods to extract relevant information from the dataset in real-time; to match data patterns that are found to psychological states (e.g. fear, stress, anger); and to perform simulation and reasoning about these states to derive predictions about potential future developments. The intelligent system will use this output to provide support for police officers and (formal) guardians in both detecting, decreasing and avoiding (the number of) incidents in large-scale events.

dr. mr. Charlotte Gerritsen

About dr. mr. Charlotte Gerritsen


Charlotte Gerritsen studied Law and Criminology at the VU University Amsterdam. After her graduation, she started working as a PhD student at the Department of Artificial Intelligence at the Faculty of Sciences at the same university. In her doctoral research (completed in 2010), she has focused on the possibilities of using techniques of Artificial Intelligence in the field of criminology. She is currently a researcher at the NSCR and working on two interdisciplinary projects.

Within the Simulation-based Training and Resilience in Emergencies and Stressful Situations (STRESS) project focuses on virtual aggression training. Professionals with public duties are regularly confronted with verbal aggressive behaviour. Think of those who threaten the conductor for not having to pay for public transport, or start swearing because they get a parking ticket. Such confrontations with verbal aggression can lead to psychological problems and impaired functioning in employees. To train these professionals with good aggression to go and ensure that situations do not escalate, the NSCR is working with the University on the STRESS project. This project developed a virtual training for employees of the public transport company (GVB) and the Police Academy. The main learning objective of the training is to recognize different types of aggression and select the matching procedure.

The Simulation-Based Prediction and Analysis of Collective Emotional States (SPACES) project focuses on predicting undesirable behaviour (such as aggression) in big crowds. Through simulation techniques it is possible to predict the spread of emotions about a group of people. The simulation model of the input is formed based on text analysis of messages posted on social media. By analysing these messages at runtime it is possible to determine emotion in the crowd, linking it to predict and the development of the emotion of the group.

Charlotte is a member of the Criminal Events Cluster and the Computational Criminology Cluster.

View All Posts

2017

Andre, Krouwel; Yordan, Kutiyski; van Prooijen, J W; Johan, Martinsson; Elias, Markstedt

Does extreme political ideology predict conspiracy beliefs, economic evaluations and political trust? Evidence from Sweden Journal Article

Journal of Social and Political Psychology, 5 (2), pp. 435-462, 2017, ISSN: 2195-3325.

Links | BibTeX