Logo des Repositoriums

Auflistung nach Schlagwort "Conversational User Interfaces"

1 - 3 von 3
  • Konferenzbeitrag
    Age-Related Differences in Preferences for Using Voice Assistants
    (Mensch und Computer 2021 - Tagungsband, 2021) Gollasch, David; Weber, Gerhard
    In the past fewyears, voice assistants have become broadly available in different forms of presentation and devices – not only as a personal assistant within smartphones but as smart speakers, within TV sets or as part of an in-car infotainment system. Furthermore, we live in an ageing society and considering elderly people as users of voice assistants gains more relevance driven by both trends. The goal of this study is to identify the specific age-related preferences of older people when using a conversational user interface in form of a voice assistant. We conducted a survey based on 26 elderlyrelated communication strategies among participants of different age. The participants had to evaluate the strategies according to their own preferences for using voice assistants. As a result, we identified 11 preferences specific to older users. Surprisingly, most of the communication strategies, when applied to voice assistants, seem to be relevant for users of all ages, and a few of the communication strategies do not apply when used in voice assistants. The preferences specific to older people help to develop new guidelines for voice user interfaces or conversational user interfaces in general. They do not automatically lead to those guidelines but provide a foundation to derive requirements, develop guidelines and evaluate those guidelines by means of user-based usability tests.
  • Workshopbeitrag
    An Explainability Case-Study for Conversational User Interfaces in Walk-Up-And-Use Contexts
    (Mensch und Computer 2021 - Workshopband, 2021) Schrills, Tim; Schmid, Leon; Jetter, Hans-Christian; Franke, Thomas
    interfaces (CUI) miss requirements for good usability, e.g. sufficient feedback regarding system status. Within a user-centred design process we created different design approaches to explain the CUI’s state. A prototypical explainable conversational user interface (XCUI) was developed, which explains its state by means of representations of (1) confidence, (2) intent alternatives, (3) entities, and (4) a context time line. The XCUI was then tested in a user study (N = 49) and compared with a conventional CUI in terms of user satisfaction and task completion time. Results indicated that completion time and satisfaction improvement were dependent on specific task characteristics. The effects of the implemented XCUI features potentially resulted from task-specific needs for explanation. This could be based on the tasks’ different complexity indicating the potential need for adaptive presentation of explainability features.
  • Konferenzbeitrag
    What Did I Say Again? Relating User Needs to Search Outcomes in Conversational Commerce
    (Proceedings of Mensch und Computer 2024, 2024) Schott, Kevin; Papenmeier, Andrea; Hienert, Daniel; Kern, Dagmar
    Recent advances in natural language processing and deep learning have accelerated the development of digital assistants. In conversational commerce, these assistants help customers find suitable products in online shops through natural language conversations. During the dialogue, the assistant identifies the customer’s needs and preferences and subsequently suggests potentially relevant products. Traditional online shops often allow users to filter search results based on their preferences using facets. Selected facets can also serve as a reminder of how the product base was filtered. In conversational commerce, however, the absence of facets and the use of advanced natural language processing techniques can leave customers uncertain about how their input was processed by the system. This can hinder transparency and trust, which are critical factors influencing customers’ purchase intentions. To address this issue, we propose a novel text-based digital assistant that, in the product assessment step, explains how specific product aspects relate to the user’s previous utterances to enhance transparency and facilitate informed decision-making. We conducted a user study (N=135) and found a significant increase in user-perceived transparency when natural language explanations and highlighted text passages were provided, demonstrating their potential to extend system transparency to the product assessment step in conversational commerce.