Logo des Repositoriums

Auflistung nach Autor:in "Buschek, Daniel"

1 - 10 von 17
  • Workshopbeitrag
    Autocompletion as a Basic Interaction Concept for User-Centered AI
    (Mensch und Computer 2020 - Workshopband, 2020) Lehmann, Florian; Buschek, Daniel
    With this position paper we propose that autocompletion can be interpreted as a basic interaction concept in the interaction between humans and systems using artificial intelligence (AI). Autocompletion is well known from text input where the system predicts intended user input, e.g. in search engines. In our research on human-AI collaboration we observe parallels to such textual autocompletion but in different application contexts, such as text generation, mock-up generation, and layout solvers. We compare exemplary related work to highlight autocompletion as a reoccurring and reusable interaction concept. We discuss that identifying underlying interaction primitives in user-centered AI can help to inform concrete design solutions for interactions and user interfaces, and could be a starting point for future research in this area.
  • Konferenzbeitrag
    Behaviour-Aware Mobile Touch Interfaces
    (Ausgezeichnete Informatikdissertationen 2018, 2019) Buschek, Daniel
  • Dissertation
    Behaviour-aware mobile touch interfaces
    (2018) Buschek, Daniel
    Mobile touch devices have become ubiquitous everyday tools for communication, information, as well as capturing, storing and accessing personal data. They are often seen as personal devices, linked to individual users, who access the digital part of their daily lives via hand-held touchscreens. This personal use and the importance of the touch interface motivate the main assertion of this thesis: Mobile touch interaction can be improved by enabling user interfaces to assess and take into account how the user performs these interactions. This thesis introduces the new term "behaviour-aware" to characterise such interfaces. These behaviour-aware interfaces aim to improve interaction by utilising behaviour data: Since users perform touch interactions for their main tasks anyway, inferring extra information from said touches may, for example, save users' time and reduce distraction, compared to explicitly asking them for this information (e.g. user identity, hand posture, further context). Behaviour-aware user interfaces may utilise this information in different ways, in particular to adapt to users and contexts. Important questions for this research thus concern understanding behaviour details and influences, modelling said behaviour, and inference and (re)action integrated into the user interface. In several studies covering both analyses of basic touch behaviour and a set of specific prototype applications, this thesis addresses these questions and explores three application areas and goals: 1) Enhancing input capabilities – by modelling users' individual touch targeting behaviour to correct future touches and increase touch accuracy. The research reveals challenges and opportunities of behaviour variability arising from factors including target location, size and shape, hand and finger, stylus use, mobility, and device size. The work further informs modelling and inference based on targeting data, and presents approaches for simulating touch targeting behaviour and detecting behaviour changes. 2) Facilitating privacy and security – by observing touch targeting and typing behaviour patterns to implicitly verify user identity or distinguish multiple users during use. The research shows and addresses mobile-specific challenges, in particular changing hand postures. It also reveals that touch targeting characteristics provide useful biometric value both in the lab as well as in everyday typing. Influences of common evaluation assumptions are assessed and discussed as well. 3) Increasing expressiveness – by enabling interfaces to pass on behaviour variability from input to output space, studied with a keyboard that dynamically alters the font based on current typing behaviour. Results show that with these fonts users can distinguish basic contexts as well as individuals. They also explicitly control font influences for personal communication with creative effects. This thesis further contributes concepts and implemented tools for collecting touch behaviour data, analysing and modelling touch behaviour, and creating behaviour-aware and adaptive mobile touch interfaces. Together, these contributions support researchers and developers in investigating and building such user interfaces. Overall, this research shows how variability in mobile touch behaviour can be addressed and exploited for the benefit of the users. The thesis further discusses opportunities for transfer and reuse of touch behaviour models and information across applications and devices, for example to address tradeoffs of privacy/security and usability. Finally, the work concludes by reflecting on the general role of behaviour-aware user interfaces, proposing to view them as a way of embedding expectations about user input into interactive artefacts.
  • Konferenzbeitrag
    Comparing Concepts for Embedding Second-Language Vocabulary Acquisition into Everyday Smartphone Interactions
    (Mensch und Computer 2021 - Tagungsband, 2021) Schneegass, Christina; Sigethy, Sophia; Eiband, Malin; Buschek, Daniel
    We present a three-week within-subject field study comparing three mobile language learning (MLL) applications with varying levels of integration into everyday smartphone interactions: We designed a novel (1) UnlockApp that presents a vocabulary task with each authentication event, nudging users towards short frequent learning session. We compare it with a (2) NotificationApp that displays vocabulary tasks in a push notification in the status bar, which is always visible but learning needs to be user-initiated, and a (3) StandardApp that requires users to start in-app learning actively. Our study is the first to directly compare these embedding concepts for MLL, showing that integrating vocabulary learning into everyday smartphone interactions via UnlockApp and NotificationApp increases the number of answers. However, users show individual subjective preferences. Based on our results, we discuss the trade-off between higher content exposure and disturbance, and the related challenges and opportunities of embedding learning seamlessly into everyday mobile interactions.
  • Zeitschriftenartikel
    Editorial
    (i-com: Vol. 19, No. 3, 2021) Buschek, Daniel; Loepp, Benedikt; Ziegler, Jürgen
  • Zeitschriftenartikel
    Examining Autocompletion as a Basic Concept for Interaction with Generative AI
    (i-com: Vol. 19, No. 3, 2021) Lehmann, Florian; Buschek, Daniel
    Autocompletion is an approach that extends and continues partial user input. We propose to interpret autocompletion as a basic interaction concept in human-AI interaction. We first describe the concept of autocompletion and dissect its user interface and interaction elements, using the well-established textual autocompletion in search engines as an example. We then highlight how these elements reoccur in other application domains, such as code completion, GUI sketching, and layouting. This comparison and transfer highlights an inherent role of such intelligent systems to extend and complete user input, in particular useful for designing interactions with and for generative AI. We reflect on and discuss our conceptual analysis of autocompletion to provide inspiration and a conceptual lens on current challenges in designing for human-AI interaction.
  • Konferenzbeitrag
    The Human in the Infinite Loop: A Case Study on Revealing and Explaining Human-AI Interaction Loop Failures
    (Mensch und Computer 2022 - Tagungsband, 2022) Ou, Changkun; Buschek, Daniel; Mayer, Sven; Butz, Andreas
    Interactive AI systems increasingly employ a human-in-the-loop strategy. This creates new challenges for the HCI community when designing such systems. We reveal and investigate some of these challenges in a case study with an industry partner, and developed a prototype human-in-the-loop system for preference-guided 3D model processing. Two 3D artists used it in their daily work for 3 months. We found that the human-AI loop often did not converge towards a satisfactory result and designed a lab study (N=20) to investigate this further. We analyze interaction data and user feedback through the lens of theories of human judgment to explain the observed human-in-the-loop failures with two key insights: 1) optimization using preferential choices lacks mechanisms to deal with inconsistent and contradictory human judgments; 2) machine outcomes, in turn, influence future user inputs via heuristic biases and loss aversion. To mitigate these problems, we propose descriptive UI design guidelines. Our case study draws attention to challenging and practically relevant imperfections in human-AI loops that need to be considered when designing human-in-the-loop systems.
  • Konferenzbeitrag
    Make Me Laugh: Recommending Humoristic Content on the WWW
    (Mensch und Computer 2015 – Proceedings, 2015) Buschek, Daniel; Just, Ingo; Fritzsche, Benjamin; Alt, Florian
    Humoristic content is an inherent part of the World Wide Web and increasingly consumed for micro-entertainment. However, humor is often highly individual and depends on background knowledge and context. This paper presents an approach to recommend humoristic content fitting each individual user's taste and interests. In a field study with 150 participants over four weeks, users rated content with a 0-10 scale on a humor website. Based on this data, we train and apply a Collaborative Filtering (CF) algorithm to assess individual humor and recommend fitting content. Our study shows that users rate recommended content 22.6% higher than randomly chosen content.
  • Zeitschriftenartikel
    Paper2Wire – A Case Study of User-Centred Development of Machine Learning Tools for UX Designers
    (i-com: Vol. 20, No. 1, 2021) Buschek, Daniel; Anlauff, Charlotte; Lachner, Florian
    This paper reflects on a case study of a user-centred concept development process for a Machine Learning (ML) based design tool, conducted at an industry partner. The resulting concept uses ML to match graphical user interface elements in sketches on paper to their digital counterparts to create consistent wireframes. A user study (N=20) with a working prototype shows that this concept is preferred by designers, compared to the previous manual procedure. Reflecting on our process and findings we discuss lessons learned for developing ML tools that respect practitioners’ needs and practices.
  • Konferenzbeitrag
    Paper2Wire: a case study of user-centred development of machine learning tools for UX designers
    (Mensch und Computer 2020 - Tagungsband, 2020) Buschek, Daniel; Anlauff, Charlotte; Lachner, Florian
    This paper reflects on a case study of a user-centred concept development process for a Machine Learning (ML) based design tool, conducted at an industry partner. The resulting concept uses ML to match graphical user interface elements in sketches on paper to their digital counterparts to create consistent wireframes. A user study (N=20) with a working prototype shows that this concept is preferred by designers, compared to the previous manual procedure. Reflecting on our process and findings we discuss lessons learned for developing ML tools that respect practitioners’ needs and practices.