Publications

Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use visible to all users through two new shared objects: user-defined agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work. 

Interactive systems are commonly prototyped as web applications. This approach enables studies with functional prototypes on a large scale. However, setting up these studies can be complex due to implementing experiment procedures, integrating questionnaires, and data logging. To enable such user studies, we developed the software system StudyAlign which offers: 1) a frontend for participants, 2) an admin panel to manage studies, 3) the possibility to integrate questionnaires, 4) a JavaScript library to integrate data logging into prototypes, and 5) a backend server for persisting log data, and serving logical functions via an API to the different parts of the system. With our system, researchers can set up web-based experiments and focus on the design and development of interactions and prototypes. Furthermore, our systematic approach facilitates the replication of studies and reduces the required effort to execute web-based user studies. We conclude with reflections on using StudyAlign for conducting HCI studies online.

Prompting-based user interfaces (UIs) shift the task of defining and accessing relevant functions from developers to users. However, how UIs shape this flexibility has not yet been investigated explicitly. We explored interaction with Large Language Models (LLMs) over four years, before and after the rise of general-purpose LLMs: (1) Our survey (N=121) elicited how users envision to delegate writing tasks to AI. This informed a conversational UI design. (2) A user study (N=10) revealed that people regressed to using short command-like prompts. (3) When providing these directly as shortcuts in a toolbar UI, in addition to prompting, users in our second study (N=12) dynamically switched between specified and flexible AI functions. We discuss functional flexibility as a new theoretical construct and thinking tool. Our work highlights the value of moving beyond conversational UIs, by considering how different UIs shape users' access to the functional space of generative AI models.

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.

Mobile word suggestions can slow down typing, yet are still widely used. To investigate the apparent benefits beyond speed, we analyzed typing behavior of 15,162 users of mobile devices. Controlling for natural typing speed (a confounding factor not considered by prior work), we statistically show that slower typists use suggestions more often but are slowed down by doing so. To better understand how these typists leverage suggestions -- if not to improve their speed -- we extract eight usage strategies, including completion, correction, and next-word prediction. We find that word characteristics, such as length or frequency, along with the strategy, are predictive of whether a user will select a suggestion. We show how to operationalize our findings by building and evaluating a predictive model of suggestion selection. Such a model could be used to augment existing suggestion algorithms to consider people's strategic use of word predictions beyond speed and keystroke savings.

Machine learning models provide functions to transform and generate image and text data. This promises powerful applications but it remains unclear how users can interact with these models. With my research, I focus on designing, implementing, and evaluating functional prototypes for understanding human-AI interactions. Methodologically, I focus on web-based experiments with a mixed-methods approach. Furthermore, I use these prototypes and generative models as a material to understand fundamental concepts in human-AI interactions, such as initiative, intent, and control. In an already conducted study, for example, I showed that the levels of initiative and control afforded by the UI influence perceived authorship when writing text. For the future, I plan to carry out more studies on collaborative writing. With my dissertation, I contribute to how we will build human-AI interactions and how we will collaborate with computational generative systems in future.

This paper reports on an in-depth study of electrocardiogram (ECG) biometrics in everyday life. We collected ECG data from 20 people over a week, using a non-medical chest tracker. We evaluated user identification accuracy in several scenarios and observed equal error rates of 9.15% to 21.91%, heavily depending on 1) the number of days used for training, and 2) the number of heartbeats used per identification decision. We conclude that ECG biometrics can work in the wild but are less robust than expected based on the literature, highlighting that previous lab studies obtained highly optimistic results with regard to real life deployments. We explain this with noise due to changing body postures and states as well as interrupted measures. We conclude with implications for future research and the design of ECG biometrics systems for real world deployments, including critical reflections on privacy.

Neural language models have the potential to support human writing. However, questions remain on their integration and influence on writing and output. To address this, we designed and compared two user interfaces for writing with AI on mobile devices, which manipulate levels of initiative and control: 1) Writing with continuously generated text, the AI adds text word-by-word and user steers. 2) Writing with suggestions, the AI suggests phrases and user selects from a list. In a supervised online study (N=18), participants used these prototypes and a baseline without AI. We collected touch interactions, ratings on inspiration and authorship, and interview data. With AI suggestions, people wrote less actively, yet felt they were the author. Continuously generated text reduced this perceived authorship, yet increased editing behavior. In both designs, AI increased text length and was perceived to influence wording. Our findings add new empirical evidence on the impact of UI design decisions on user experience and output with co-creative systems.