9607 research outputs found
Sort by
Don’t Get Too Excited - Eliciting Emotions in LLMs
No full textThis paper investigates the challenges of affect control in large language models (LLMs), focusing on their ability to express appropriate emotional states during extended dialogues. We evaluated state-of-the-art open-weight LLMs to assess their affective expressive range in terms of arousal and valence. Our study employs a novel methodology combining LLM-based sentiment analysis with multiturn dialogue simulations between LLMs.We quantify the models' capacity to express a wide spectrum of emotions and how they fluctuate during interactions. Our findings reveal significant variations among LLMs in their ability to maintain consistent affect, with some models demonstrating more stable emotional trajectories than others. Furthermore, we identify key challenges in affect control, including difficulties in producing and maintaining extreme emotional states and limitations in adapting affect to changing conversational contexts. These findings have important implications for the development of more emotionally intelligent AI systems and highlight the need for improved affect modelling in LLMs
On the Dynamics of Affective States During Play and the Role of Confusion.
Get PDFVideo game designers often view confusion as undesirable, yet it is inevitable, as new players must adapt to new interfaces and mechanics in an increasingly varied and innovative game market, which is more popular than ever. Research suggests that confusion can contribute to a positive experience, potentially motivating players to learn. The state of confusion in video games should be further investigated to gain more insight into the learning experience of play and how it affects the player experience. In this article, we design a study to collect learning-related affects for users playing a game prototype that intentionally confuses the player. We assess the gathered affects against a complex learning model, affirming that, in specific instances, the player experience aligns with the learning experiences. Moreover, we identify correlations between these affects and the Player Experience Inventory constructs, particularly concerning flow experiences
Urban Data Science for Sustainable Mobility
Get PDFTransportation is a major sector of human activity fueling the climate crisis. Therefore, there is an urgent need to make mobility more sustainable. Due to contemporary urbanization, this need is particularly pressing within cities, and can be addressed through the emerging interdisciplinary field of Urban Data Science. This field combines methods from Data Science with domain knowledge of the city, making use of the increasing availability and volume of data on urban environments.In the realm of mobility, sustainability is gaining popularity as a framework for research and policy-making. Nevertheless, available data, tools, and research efforts for sustainable transportation modes like cycling are still dwarfed by those for motorized modes, constituting a considerable research gap. In addition, techno-optimist approaches to sustainability, such as the excessive supportfor car-centric motorized transportation systems, entail serious ethical pitfalls. To address these challenges, this thesis explores how Urban Data Science can ethically support human mobility that is both environmentally and socially sustainable, through the two lenses of Data and Networks. In the realm of Data, we develop an algorithm for multi-purpose spatial network simplification, and a data quality assessment pipeline tailored specifically to bicycle networks. Further, we outline pathways for incorporating data ethics into computational approaches to spatial manifestations of social inequalities. In the realm of Networks, we develop data-driven methods for the planning of bicycle networks and low-traffic neighbourhoods, and showcase their application to various cities.Lastly, we investigate the impact of transportation infrastructure on social connections in cities, quantitatively corroborating that urban highways are barriers to social ties. Stemming from various interdisciplinary collaborations, the results of this thesis cover multiple conceptual levels of Urban Data Science, from open source software development and data quality assessment to transportation network planning and the intersection of social and spatial networks. Through these efforts, this thesis advances the emerging field of Urban Data Science, showcasing the field’s potential to make human mobility more sustainable
In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review
No full textDatasets play a critical role in medical imaging research, yet issues such as label quality, shortcuts, and metadata are often overlooked. This lack of attention may harm the generalizability of algorithms and, consequently, negatively impact patient outcomes. While existing medical imaging literature reviews mostly focus on machine learning (ML) methods, with only a few focusing on datasets for specific applications, these reviews remain static – they are published once and not updated thereafter. This fails to account for emerging evidence, such as biases, shortcuts, and additional annotations that other researchers may contribute after the dataset is published. We refer to these newly discovered findings of datasets as research artifacts. To address this gap, we propose a living review that continuously tracks public datasets and their associated research artifacts across multiple medical imaging applications. Our approach includes a framework for the living review to monitor data documentation artifacts, and an SQL database to visualize the citation relationships between research artifact and dataset. Lastly, we discuss key considerations for creating medical imaging datasets, review best practices for data annotation, discuss the significance of shortcuts and demographic diversity, and emphasize the importance of managing datasets throughout their entire lifecycle. Our demo is publicly available at http://inthepicture.itu.dk/
KARRIEREWEGE: A large scale Career Path Prediction Dataset
No full textAccurate career path prediction can support many stakeholders, like job seekers, recruiters, HR, and project managers. However, publicly available data and tools for career path prediction are scarce. In this work, we introduce Karrierewege, a comprehensive, publicly available dataset containing over 500k career paths, significantly surpassing the size of previously available datasets. We link the dataset to the ESCO taxonomy to offer a valuable resource for predicting career trajectories. To tackle the problem of free-text inputs typically found in resumes, we enhance it by synthesizing job titles and descriptions resulting in Karrierewege+. This allows for accurate predictions from unstructured data, closely aligning with practical application challenges. We benchmark existing state-of-the-art (SOTA) models on our dataset and a previous benchmark and see increased performance and robustness by synthesizing the data for the free-text use cases
The Danish Business Authority’s Approach to the Ongoing Evaluation of AI Systems
No full textAI systems that work as intended when first deployed may drift over time, making increasingly inaccurate or biased decisions. Organizations therefore need to ensure the proper ongoing functioning of their AI systems, especially as the world around these AI systems changes. In this article, we describe the strategies used by the Danish Business Authority, an early public-sector adopter of AI, to ensure the effective ongoing evaluation of AI systems and provide four recommendations for other organizations
Sustainable democracy. Potentials and pitfalls of young citizens’ informed and democratic citizenship
No full textThis objective of this paper is framed through a triangulation of three points: young citizens are the bearers of future sustainable Democracy (Mascheroni & Murri 2017; Stald 2024); informed citizenship (redefined) is vital for the foundation of sustainable Democracy (Bennett 2008; Mihailidis, 2014); sustainable Democracy depends on the collective ability to allow new forms of information and informed citizenship (Dauer et al., 2021; Stald, 2023), and to support young generations in developing democratic self-efficacy (Cortesei et al., 2020; Stald & Balle, 2024). Sustainable Democracy usually describes development of new democracies by learning from established democracies (Przeworski, 1995) or a connection between sustainability goals and democratic ambition (Ward, 2008). In this paper, however, the term frames the challenge of sustaining Democracy while innovating the idea, foundation, and practices of Democracy in alignment with societal development, informed citizenship, and young people’s experiences and life-practices. The paper draws on a study (2024) that investigates 16–18-year-old Danes’ experiences with being informed, democratic, and participating, digital citizens, including questions of trust and critical reflexivity. The study comprises interviews with 20 highschool students and written essays from 75 highschool students. The informants demonstrate knowledge and opinions about international, national, and local topics. The pivotal point is the perception of politics and Democracy as something that takes place elsewhere, with/among someone who knows more and has more authority. But the informants eventually realize that politics and Democracy are also relatable to them in their everyday lives. This is a vital element in sustaining the foundations of Democracy.<br/
Outsourcing response-ability:Tales from ‘agile’ governance
No full textAs Western countries have deepened their levels of digitalisation of the public sector, governments have become increasingly interested in abandoning, or at least loosening, some of the more rigid bureaucratic structures governing the state apparatus and experimenting with the agile methodologies that grew out of Silicon Valley around the turn of the millennium. In this chapter, we argue that this increasingly widespread agile public digitalisation style is creating a need to pay more attention to the development and design, delivery, efficiency, and governance of digital public services, the infrastructures they rely on, and the societal impact of this so-called agile transformation.We suggest understanding this problem through the prism of response-ability, an empirically derived concept consisting of three distinct but overlapping dimensions regarding the ability of the state to (a) respond fast and flexibly, (b) be held accountable for its decisions, and (c) be responsive to citizens and stakeholders. These three dimensions have always been central to democratic statehood but are re-actualised and gain new meaning as they become part of the processes of public digitalisation and agile transformation.The chapter consists of four sections, each presenting a theme within agile and digital public transformation, in relation to which the concept of response-ability comes into play. The themes are governance, insourcing, legacy and maintenance, and citizen involvement. The sections draw on the authors’ knowledge and empirical studies of the public sectors in the Nordic countries and the UK, and draw on various data types, from interviews with key actors to field visits and publicly available documents, as well as, for some of us, previous industry experience.This chapter discusses the governance consequences of the alleged ‘agile transformation’ of digitalising Western states. This transformation process, a consequence of the widespread digitalisation efforts of Western states, builds on a set of values and routines from software engineering which advocate for change in the project management logics of digital public service provision. An ‘agile’ public sector promises to deliver not just more thoroughly digitalised public services, but also better digitalisation by enhancing the speed, flexibility, and innovative capabilities of IT project management. However, such an agile transformation is not easily accomplished, and its implications for the welfare state and traditionally bureaucratic state apparatuses remain unclear. Through the prism of response-ability, we problematise the state's attempted agile transformation from four perspectives – governance, sourcing, legacy and maintenance, and citizenship and user involvement – drawing on empirical studies of the public sectors in the Nordic countries and the UK
Identifying Open Challenges in Language Identification
No full textAutomatic language identification is a core problem of many Natural LanguageProcessing (NLP) pipelines. A wide variety of architectures and benchmarks havebeen proposed with often near-perfect performance. Although previousstudies have focused on certain challenging setups (i.e. cross-domain, shortinputs), a systematic comparison is missing. We propose a benchmark that allows us to test for the effect of input size, training data size, domain, number oflanguages, scripts, and language families on performance. We evaluatefive popular models on this benchmark and identify which open challengesremain for this task as well as which architectures achieve robust performance. Wefind that cross-domain setups are the most challenging (although arguably mostrelevant), and that number of languages, variety in scripts, and variety inlanguage families have only a small impact on performance. We also contributepractical takeaways: training with 1,000 instances per language and a maximuminput length of 100 characters is enough for robust language identification.Based on our findings, we train an accurate (94.41{\%}) multi-domain languageidentification model on 2,034 languages, for which we also provide an analysisof the remaining errors