Albrecht Schmidt

Luke Haliburton, Sinksar Ghebremedhin, Robin Welsch et al. · cmu

In a world increasingly reliant on artificial intelligence, it is more important than ever to consider the ethical implications of artificial intelligence on humanity. One key under-explored challenge is labeler bias, which can create inherently biased datasets for training and subsequently lead to inaccurate or unfair decisions in healthcare, employment, education, and law enforcement. Hence, we conducted a study to investigate and measure the existence of labeler bias using images of people from different ethnicities and sexes in a labeling task. Our results show that participants possess stereotypes that influence their decision-making process and that labeler demographics impact assigned labels. We also discuss how labeler bias influences datasets and, subsequently, the models trained on them. Overall, a high degree of transparency must be maintained throughout the entire artificial intelligence training process to identify and correct biases in the data as early as possible.

Fiona Draxler, Anna Werner, Florian Lehmann et al.

Human-AI interaction in text production increases complexity in authorship. In two empirical studies (n1 = 30 & n2 = 96), we investigate authorship and ownership in human-AI collaboration for personalized language generation. We show an AI Ghostwriter Effect: Users do not consider themselves the owners and authors of AI-generated text but refrain from publicly declaring AI authorship. Personalization of AI-generated texts did not impact the AI Ghostwriter Effect, and higher levels of participants' influence on texts increased their sense of ownership. Participants were more likely to attribute ownership to supposedly human ghostwriters than AI ghostwriters, resulting in a higher ownership-authorship discrepancy for human ghostwriters. Rationalizations for authorship in AI ghostwriters and human ghostwriters were similar. We discuss how our findings relate to psychological ownership and human-AI interaction to lay the foundations for adapting authorship frameworks and user interfaces in AI in text-generation tasks.

David Bethge, Philipp Hallgarten, Tobias Grosse-Puppendahl et al.

There is a growing need for sparse representational formats of human affective states that can be utilized in scenarios with limited computational memory resources. We explore whether representing neural data, in response to emotional stimuli, in a latent vector space can serve to both predict emotional states as well as generate synthetic EEG data that are participant- and/or emotion-specific. We propose a conditional variational autoencoder based framework, EEG2Vec, to learn generative-discriminative representations from EEG data. Experimental results on affective EEG recording datasets demonstrate that our model is suitable for unsupervised EEG modeling, classification of three distinct emotion categories (positive, neutral, negative) based on the latent representation achieves a robust performance of 68.49%, and generated synthetic EEG sequences resemble real EEG data inputs to particularly reconstruct low-frequency signal components. Our work advances areas where affective EEG representations can be useful in e.g., generating artificial (labeled) training data or alleviating manual feature extraction, and provide efficiency for memory constrained edge computing applications.

David Bethge, Philipp Hallgarten, Ozan Özdenizci et al.

Electroencephalography (EEG) is shown to be a valuable data source for evaluating subjects' mental states. However, the interpretation of multi-modal EEG signals is challenging, as they suffer from poor signal-to-noise-ratio, are highly subject-dependent, and are bound to the equipment and experimental setup used, (i.e. domain). This leads to machine learning models often suffer from poor generalization ability, where they perform significantly worse on real-world data than on the exploited training data. Recent research heavily focuses on cross-subject and cross-session transfer learning frameworks to reduce domain calibration efforts for EEG signals. We argue that multi-source learning via learning domain-invariant representations from multiple data-sources is a viable alternative, as the available data from different EEG data-source domains (e.g., subjects, sessions, experimental setups) grow massively. We propose an adversarial inference approach to learn data-source invariant representations in this context, enabling multi-source learning for EEG-based brain-computer interfaces. We unify EEG recordings from different source domains (i.e., emotion recognition datasets SEED, SEED-IV, DEAP, DREAMER), and demonstrate the feasibility of our invariant representation learning approach in suppressing data-source-relevant information leakage by 35% while still achieving stable EEG-based emotion classification performance.

Pavithren V S Pakianathan, Rania Islambouli, Diogo Branco et al.

Individuals are increasingly generating substantial personal health and lifestyle data, e.g. through wearables and smartphones. While such data could transform preventative care, its integration into clinical practice is hindered by its scale, heterogeneity and the time pressure and data literacy of healthcare professionals (HCPs). We explore how large language models (LLMs) can support sensemaking of patient-generated health data (PGHD) with automated summaries and natural language data exploration. Using cardiovascular disease (CVD) risk reduction as a use case, 16 HCPs reviewed multimodal PGHD in a mixed-methods study with a prototype that integrated common charts, LLM-generated summaries, and a conversational interface. Findings show that AI summaries provided quick overviews that anchored exploration, while conversational interaction supported flexible analysis and bridged data-literacy gaps. However, HCPs raised concerns about transparency, privacy, and overreliance. We contribute empirical insights and sociotechnical design implications for integrating AI-driven summarization and conversation into clinical workflows to support PGHD sensemaking.

David Haag, Devender Kumar, Sebastian Gruber et al.

We evaluated the viability of using Large Language Models (LLMs) to trigger and personalize content in Just-in-Time Adaptive Interventions (JITAIs) in digital health. As an interaction pattern representative of context-aware computing, JITAIs are being explored for their potential to support sustainable behavior change, adapting interventions to an individual's current context and needs. Challenging traditional JITAI implementation models, which face severe scalability and flexibility limitations, we tested GPT-4 for suggesting JITAIs in the use case of heart-healthy activity in cardiac rehabilitation. Using three personas representing patients affected by CVD with varying severeness and five context sets per persona, we generated 450 JITAI decisions and messages. These were systematically evaluated against those created by 10 laypersons (LayPs) and 10 healthcare professionals (HCPs). GPT-4-generated JITAIs surpassed human-generated intervention suggestions, outperforming both LayPs and HCPs across all metrics (i.e., appropriateness, engagement, effectiveness, and professionalism). These results highlight the potential of LLMs to enhance JITAI implementations in personalized health interventions, demonstrating how generative AI could revolutionize context-aware computing.

David Bethge, Daniel Bulanda, Adam Kozlowski et al.

Routes represent an integral part of triggering emotions in drivers. Navigation systems allow users to choose a navigation strategy, such as the fastest or shortest route. However, they do not consider the driver's emotional well-being. We present HappyRouting, a novel navigation-based empathic car interface guiding drivers through real-world traffic while evoking positive emotions. We propose design considerations, derive a technical architecture, and implement a routing optimization framework. Our contribution is a machine learning-based generated emotion map layer, predicting emotions along routes based on static and dynamic contextual data. We evaluated HappyRouting in a real-world driving study (N=13), finding that happy routes increase subjectively perceived valence by 11% (p=.007). Although happy routes take 1.25 times longer on average, participants perceived the happy route as shorter, presenting an emotion-enhanced alternative to today's fastest routing mechanisms. We discuss how emotion-based routing can be integrated into navigation apps, promoting emotional well-being for mobility use.

David Bethge, Philipp Hallgarten, Tobias Grosse-Puppendahl et al.

Deep learning based electroencephalography (EEG) signal processing methods are known to suffer from poor test-time generalization due to the changes in data distribution. This becomes a more challenging problem when privacy-preserving representation learning is of interest such as in clinical settings. To that end, we propose a multi-source learning architecture where we extract domain-invariant representations from dataset-specific private encoders. Our model utilizes a maximum-mean-discrepancy (MMD) based domain alignment approach to impose domain-invariance for encoded representations, which outperforms state-of-the-art approaches in EEG-based emotion classification. Furthermore, representations learned in our pipeline preserve domain privacy as dataset-specific private encoding alleviates the need for conventional, centralized EEG-based deep neural network training approaches with shared parameters.

Radiah Rivu, Ville Mäkelä, Sarah Prange et al.

We investigate the opportunities and challenges of running virtual reality (VR) studies remotely. Today, many consumers own head-mounted displays (HMDs), allowing them to participate in scientific studies from their homes using their own equipment. Researchers can benefit from this approach by being able to reach a more diverse study population and to conduct research at times when it is difficult to get people into the lab (cf. the COVID pandemic). We first conducted an online survey (N=227), assessing HMD owners' demographics, their VR setups, and their attitudes towards remote participation. We then identified different approaches to running remote studies and conducted two case studies for an in-depth understanding. We synthesize our findings into a framework for remote VR studies, discuss the strengths and weaknesses of the different approaches, and derive best practices. Our work is valuable for HCI researchers conducting VR studies outside labs.

Thomas Kosch, Albrecht Schmidt

Digital interaction with everyday objects has become popular since the proliferation of camera-based systems that detect and augment objects "just-in-time". Common systems use a vision-based approach to detect objects and display their functionalities to the user. Sensors, such as color and depth cameras, have become inexpensive and allow seamless environmental tracking in mobile as well as stationary settings. However, object detection in different contexts faces challenges as it highly depends on environmental parameters and the conditions of the object itself. In this work, we present three tracking algorithms which we have employed in past research projects to track and recognize objects. We show, how mobile and stationary augmented reality can be used to extend the functionalities of objects. We conclude, how common items can provide user-defined tangible interaction beyond their regular functionality.

Pascal Oser, Sebastian Feger, Paweł W. Woźniak et al.

Users of Internet of Things (IoT) devices are often unaware of their security risks and cannot sufficiently factor security considerations into their device selection. This puts networks, infrastructure and users at risk. We developed and evaluated SAFER, an IoT device risk assessment framework designed to improve users' ability to assess the security of connected devices. We deployed SAFER in a large multinational organization that permits use of private devices. To evaluate the framework, we conducted a mixed-method study with 20 employees. Our findings suggest that SAFER increases users' awareness of security issues. It provides valuable advice and impacts device selection. Based on our findings, we discuss implications for the design of device risk assessment tools, with particular regard to the relationship between risk communication and user perceptions of device complexity.

Tom Hanika, Marek Herde, Jochen Kuhn et al.

The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research objectives have been stated, there is still the need to clarify some terms such as information, knowledge, and experience in the context of CIL and to differentiate CIL from recent and ongoing research in related fields such as active learning, collaborative learning, and others. Both aspects are addressed in this paper.

Sebastian S. Feger, Sünje Dallmeier-Tiessen, Albrecht Schmidt et al.

Reproducibility should be a cornerstone of scientific research and is a growing concern among the scientific community and the public. Understanding how to design services and tools that support documentation, preservation and sharing is required to maximize the positive impact of scientific research. We conducted a study of user attitudes towards systems that support data preservation in High Energy Physics, one of science's most data-intensive branches. We report on our interview study with 12 experimental physicists, studying requirements and opportunities in designing for research preservation and reproducibility. Our findings suggest that we need to design for motivation and benefits in order to stimulate contributions and to address the observed scalability challenge. Therefore, researchers' attitudes towards communication, uncertainty, collaboration and automation need to be reflected in design. Based on our findings, we present a systematic view of user needs and constraints that define the design space of systems supporting reproducible practices.

Sebastian S. Feger, Sünje Dallmeier-Tiessen, Paweł W. Woźniak et al.

The need for data preservation and reproducible research is widely recognized in the scientific community. Yet, researchers often struggle to find the motivation to contribute to data repositories and to use tools that foster reproducibility. In this paper, we explore possible uses of gamification to support reproducible practices in High Energy Physics. To understand how gamification can be effective in research tools, we participated in a workshop and performed interviews with data analysts. We then designed two interactive prototypes of a research preservation service that use contrasting gamification strategies. The evaluation of the prototypes showed that gamification needs to address core scientific challenges, in particular the fair reflection of quality and individual contribution. Through thematic analysis, we identified four themes which describe perceptions and requirements of gamification in research: Contribution, Metrics, Applications and Scientific practice. Based on these, we discuss design implications for gamification in science.