Umeå University's logo

Objective: Although patients prefer describing their problems using words, mental health interventions are commonly evaluated using rating scales. Fortunately, recent advances in natural language processing (i.e., AI-methods) yield new opportunities to quantify people's own mental health descriptions. Our aim was to explore whether responses to open-ended questions, quantified using AI, provide additional value in measuring intervention outcomes compared to traditional rating scales.

Method: Swedish adolescents (N = 44) who received Internet-based Cognitive Behavioral Therapy (ICBT) for eight weeks completed (pre/post) scales measuring anxiety and depression and three open-ended questions (related to depression, anxiety and general mental health). The language responses were quantified using a large language model and quantitative methods to predict mental health as measured by rating scales, valence (i.e., words' positive/negative affectivity), and semantic content (i.e., meaning).

Results: Similar to the rating scales, language measures revealed statistically significant health improvements between pre and post measures such as reduced depression and anxiety symptoms and an increase in the use of words conveying positive emotions and different meanings (e.g., pre-intervention: “anxious”, depressed; post-intervention: “happy”, “the future”). Notably, the health changes identified through semantic content measures remained statistically significant even after accounting for the changes captured by the rating scales.

Conclusion: Language responses analyzed using AI-methods assessed outcomes with fewer items, demonstrating effectiveness and accuracy comparable to traditional rating scales. Additionally, this approach provided valuable insights into patients' well-being beyond mere symptom reduction, thus highlighting areas of improvement that rating scales often overlook. Since patients often prefer using natural language to express their mental health, this method could complement, and address comprehension issues associated fixed-item questionnaires.

Recent years have seen a sharply rising interest in the scientific area dedicated to the study of the use of Artificial Intelligence (AI) for Cognitive Behavioral Therapy (CBT) research and applications (AI4CBT for brevity). Yet, little is known about how this interest is realized and hence the overall status, prospects, and possible challenges of AI4CBT as a field (e.g. breadth of the field, key topics and methods, key producing countries/institutions/authors, interdisciplinary grounding). This paper addresses this gap by developing a broad-spectrum bibliometric analysis towards acquiring a comprehensive overview of the AI4CBT field. Four key dimensions are analyzed (productivity, producers, productions, and contents) along the array of bibliographic metrics, including production trends over time, leading contributors at various levels, co-authorship, citation, and keywords co-occurrence networks, publication formats, key venues, methodological trends, and disciplinary assessment. The paper concludes by framing the status of AI4CBT as a scientific field, allowing to tie it to scientific and applicative challenges and opportunities that AI4CBT may encounter and offer as it further develops.

Truly realistic models for policy making require multiple aspects of life, realistic social behaviour and the ability to simulate millions of agents. Current state of the art Agent-based models only achieve two of these requirements. Models that prioritise realistic social behaviour are not easily scalable because the complex deliberation takes into account all information available at each time step for each agent. Our framework uses context to considerably narrow down the information that has to be considered. A key property of the framework is that it can dynamically slide between fast deliberation and complex deliberation. Context is expanded based on necessity. We introduce the elements of the framework, describe the architecture and show a proof-of-concept implementation. We give first steps towards validation using this implementation.

Simulating for policy making can require modelling multiple aspects of life, realistic social behaviour and the ability to simulate up to millions of agents [1]. However realistic models are not easily scalable due to the complex deliberation that takes into account all information at every time step which is slow. Explicitly taking into account context in the deliberation can increase scalability, through a complexity by need principle. The Dynamic Context-Sensitive Deliberation (DCSD) framework uses minimal information when possible, but gradually draws in more information when necessary. To validate whether DCSD can increase scalability while retaining realism we implement DCSD into an example large scale model, the Agent-based Social Simulation of the Coronavirus Crisis (ASSOCC). We compare the original deliberation from the ASSOCC model with the implemented DCSD. We conclude that DCSD can increase scalability while retaining realism in large scale social simulation models.

Whereas hackathons are widespread within and outside academia and have been argued to be a valid pedagogical method for teaching interdisciplinarity, no detailed frameworks or methods are available for conceptualizing and organizing educational hackathons, i.e., hackathons dedicated to best achieving pedagogic objectives. This paper is dedicated to introducing EDUCational Hackathons for learning how to solve Interdisciplinary Challenges (EDUCHIC) through: (1) defining the fundamental principles for framing an activity as an EDUCHIC, integrating principles from pedagogical methods, hackathon organization, and interdisciplinarity processes; (2) describing general properties that EDUCHIC possess as a consequence of the interaction of the fundamental principles; (3) developing operational guidelines for streamlining the practical organization of EDUCHIC, including an exhaustive end-to-end process covering all the steps for organizing EDUCHIC and practical frames for carrying the key decisions to be made in this process; and (4) a demonstration of these guidelines through illustrating their application for organizing a concrete EDUCHIC.

Anxiety is one of the most basic emotional states and also the most common disorder. AI agents however are typically focused on maximising performance, concentrating on expected values and disregarding the degree of exposure to uncertainty. This paper introduces a formalism derived from Partially Observable Markov Decision Processes (POMDPs) to give the first model based on cognitive psychology of the anxiety induced by epistemic uncertainty (i.e. the lack of precision of knowledge about the current state of the world). An algorithm to generate policies balancing reward maximisation and anxiety reduction is given. It is then used on a classical example to demonstrate how this can lead in some cases to a dramatic reduction of epistemic uncertainty for nearly no cost and thus a more human-friendly reward optimisation. The empirical validation shows results reminiscent of behaviours that cognitive psychology identifies as coping mechanisms to anxiety.

Emotion and cognition are at the core of human behaviour and modelling human behaviour is at the core of social simulation. Using a bibliometric analysis of publications connecting agent-based modelling with cognition (sense), emotion (sensibility), or both, this study describes the evolution of the field, explores trends, and identifies existing gaps, and proposes potential future developments. Our results indicate that Sense and Sensibility research tracks have seen a significant growth over the last 30 years and a sustained interest with regards to the agent-based modelling community as a whole. However, results also show that such research has issues reaching beyond computer science venues and that, despite its important demands in terms of competence building, relatively few researchers become regular contributors of the field.

In agent-based social simulations (ABSS), an artificial population of intelligent agents that imitate human behavior is used to investigate complex phenomena within social systems. This is particularly useful for decision makers, where ABSS can provide a sandpit for investigating the effects of policies prior to their implementation. During the Covid-19 pandemic, for instance, sophisticated models of human behavior enable the investigation of the effects different interventions can have and even allow for analyzing why a certain situation occurred or why a specific behavior can be observed. In contrast to other applications of simulation, the use for policy making significantly alters the process of model building and assessment, and requires the modelers to follow different paradigms. In this chapter, we report on a tutorial that was organized as part of the ACAI 2021 summer school on AI in Berlin, with the goal of introducing agent-based social simulation as a method for facilitating policy making. The tutorial pursued six Intended Learning Outcomes (ILOs), which are accomplished by three sessions, each of which consists of both a conceptual and a practical part. We observed that the PhD students participating in this tutorial came from a variety of different disciplines, where ABSS is mostly applied as a research method. Thus, they do often not have the possibility to discuss their approaches with ABSS experts. Tutorials like this one provide them with a valuable platform to discuss their approaches, to get feedback on their models and architectures, and to get impulses for further research.

Ethical concerns regarding Artificial Intelligence technology have fueled discussions around the ethics training received by its designers. Training designers for ethical behaviour, understood as habitual application of ethical principles in any situation, can make a significant difference in the practice of research, development, and application of AI systems. Building on interdisciplinary knowledge and practical experience from computer science, moral psychology, and pedagogy, we propose a functional way to provide this training.

Despite being understated, anxiety is a critical factor affecting all levels of society, directly impacting individual decisions and with well-identified ramifications on social play, social constructs, and collective outcomes, as well as being a significant direct social toll tied to yearly trillion-USD social cost. Through a systematic literature review of social simulation research featuring models of anxiety, this paper frames the state of the art on anxiety modelling, and identifies trends and patterns in bibliographic indicators, aspects of anxiety that are modelled, how they are modelled, and their purpose and integration within agent based models. Based on these findings, this paper proposes a way forward as to structure the field as to enable the social simulation community as a whole to cover this critical aspect.