While it is often assumed that searching for information to evaluate misinformation will help identify false claims, recent work suggests that search behaviours can instead reinforce belief in misleading news, particularly when users generate queries using vocabulary from the source articles. Our research explores how different query generation strategies affect news verification and whether the way people search influences the accuracy of their information evaluation. A mixed-methods approach was used, consisting of three parts: (1) an analysis of existing data to understand how search behaviour influences trust in fake news (2) a simulation of query generation strategies using a Large Language Model (LLM) to assess the impact of different query formulations on search result quality, and (3) a user study to examine how 'Boost' interventions in interface design can guide users to adopt more effective query strategies. The results show that search behaviour significantly affects trust in news, with successful searches involving multiple queries and yielding higher-quality results. Queries inspired by different parts of a news article produced search results of varying quality, and weak initial queries improved when reformulated using full SERP information. Although 'Boost' interventions had limited impact, the study suggests that interface design encouraging users to thoroughly review search results can enhance query formulation. This study highlights the importance of query strategies in evaluating news and proposes that interface design can play a key role in promoting more effective search practices, serving as one component of a broader set of interventions to combat misinformation.

This study examines the use of Motivational Interviewing (MI) principles in a GPT-4-based chatbot, MIcha, to promote behaviour change. We conducted a pre-registered randomised controlled trial to assess the integration of MI techniques in conversational agents, aiming to support users’ behaviour change through guided self-reflection and identify how users interact with large language model (LLM)-based systems in this context. Results indicate that short conversations with LLM-based chatbots are successful at increasing users’ readiness to change and usage of MI principles during text generation can effectively mitigate potential harms. Additionally, we identified distinct user behaviour types — cooperative, reflective, and pre-informed—that significantly influenced the outcomes of interactions. These findings demonstrate the potential of MI principles in enhancing the efficacy of conversational agents for behaviour change and highlight the importance of user behaviour in shaping interaction dynamics. • Brief LLM chats on behaviour change goals significantly boost readiness to change. • Motivational interviewing can significantly reduce potential harms in LLM outputs. • User behaviour types heavily influence conversation outcome and success.

Conversational agents are increasingly used to address emotional needs on top of information needs. One use case of increasing interest are counselling-style mental health and behaviour change interventions, with large language model (LLM)-based approaches becoming more popular. Research in this context so far has been largely system-focused, foregoing the aspect of user behaviour and the impact this can have on LLM-generated texts. To address this issue, we share a dataset containing text-based user interactions related to behaviour change with two GPT-4-based conversational agents collected in a preregistered user study. This dataset includes conversation data, user language analysis, perception measures, and user feedback for LLM-generated turns, and can offer valuable insights to inform the design of such systems based on real interactions.

Success of weight loss programmes can be highly dependent on the provision of appropriate information. The guidance individuals should receive varies depending on their motivational state. If information systems were able to discern a user’s current stage of change and use this information to retrieve appropriate support strategies, this could greatly increase their impact on the implementation and maintenance of the behavioural changes necessary for successful weight loss. This PhD project explores the feasibility of predicting a person’s stage of change in the context of weight loss based on the personal information they share in their language. The goal of the project is to enable a conversational information system to provide the informational and motivational support the user is seeking at any given point of the change process. In this paper, we outline the proposed research plan and methodologies and describe expected challenges of the project.

Refugees trying to get to Europe via the Mediterranean often face human rights violations. The present situation is not in line with the UN's SDG's 10 and 16. We present Argo: a semi-automatically created vessel classification dataset focused on small boats, with the aim to enable NGOs and the public to detect refugee boats in satellite imagery. We achieve a classification recall of 91% on small ships. With a tool developed on top of the results presented here, NGOs could collect information and hold institutions participating in illegal activities accountable.

Health behaviour change is a difficult and prolonged process that requires sustained motivation and determination. Conversa- tional agents have shown promise in supporting the change process in the past. One therapy approach that facilitates change and has been used as a framework for conversational agents is motivational interviewing. However, existing implementations of this therapy approach lack the deep understanding of user utterances that is essential to the spirit of motivational interviewing. To address this lack of understanding, we introduce the GLoHBCD, a German dataset of naturalistic language around health behaviour change. Data was sourced from a popular German weight loss forum and annotated using theoretically grounded motivational interviewing categories. We describe the process of dataset construction and present evaluation results. Initial experiments suggest a potential for broad applicability of the data and the resulting classifiers across different behaviour change domains. We make code to replicate the dataset and experiments available on Github.

Motivational factors play a significant role in weight loss. Providing appropriate support based on an individual’s motivational level could be a deciding factor in weight loss success. Considering the high cost of obesity to public health care, a system with the ability to assess motivation could benefit individuals and the public alike. As self-report measures are not always available and would be tedious to use on a regular basis, one way to achieve this understanding could be the interpretation of natural language. This project studies the feasibility of using conversational agents to measure motivation by engaging users in natural conversation during weight loss. This approach could be a good means of tracking motivation, as it is cheap and accessible and can model motivation in a more natural and engaging way than self-report measures.