Integrating Sentiment Analysis in Real-time Crowd Management

Within this project we develop a computer system capable of managing crowds during events by combining automated emotion recognition and dynamical modelling of deviant behaviour. By training crowd managers through simulated scenarios and by providing real time support we’ll enable them to intervene in the right place at the right time.

Contact person: Charlotte Gerritsen

Development of Chatbots for Depression Patients – A Cognition-Inspired Approach

The research aims to develop a cognitive-inspired chatbot memory system for mental health, focusing on dynamic memory management, crucial information extraction, request interpretation, and response organization, integrating natural language understanding and knowledge graphs.

Contact person: Chaohui Guo

SMART: An AI-supported Lifestyle App for People with Osteoarthritis

Individuals with osteoarthritis experience pain and stiffness when moving, which hinders their daily activities. Although various non-surgical treatment options exist, they are often underutilized in practice. In the SMART project, we aim to develop and evaluate a personalized self-management app that supports patients with osteoarthritis using expert knowledge and Artificial Intelligence models.The project is funded by ZonMW and led by Hogeschool Utrecht.

Contact person: Michel Klein

A Customized LLM-based Chatbot for Undocumented People

Access to health is a fundamental human right that is enshrined in the statutes of the World Health Organisation (WHO). However, undocumented migrant communities have for long experienced marginalisation and discrimination in accessing health care services, and suffer from ill-health disproportionately. In this project, we have co-designed a chatbot based on a large language model (LLM) that can help undocumented people and their helpers to get the information needed when looking for medical attention. The project is funded by the VU Network Institute.

Contact person: Michel Klein

Visualizing the Future: The Role of Virtual Reality in Promoting Environmental Sustainability

This project aims to assess whether VR technology can positively change multiple human behaviours in an environmental context. One way to study this is by evaluating spillover effects of behavioral interventions. Spillover effects assess whether individuals who have adopted more sustainable behaviour in one domain (eating less meat) will also become more susceptible to changing their behaviour in another domain (reduced energy consumption). We will develop an environment where participants interact with various scenarios to increase awareness and support behavior change regarding the environment through digital intervention.

This is a project together with the IVM.

Contact person: Charlotte Gerritsen

Virtual Therapist for Mental Health Support

In recent years, therapies have gotten attention as an intervention for mental health problems. However, it’s hard to find enough time and resources for undergoing proper therapy sessions. Therefore, the aim of this project is to develop an AI supported therapy agent, i.e., which will offer real-time emotion regulation techniques and counseling, promoting positive mental health behavior change. The agent will receive information about the emotional state of the user from their smart devices, i.e., smart watch, smartphone etc.

Mental models and LLMs for behaviour change

In this research project, we investigate how mental models in large language models (LLMs) influence the interaction between the LLM and the user. By enabling LLMs to understand and reason about users’ mental models, we aim to develop more personalized recommendations that can drive meaningful behavior change.

Contact person: Ilke Asal