Refine
Year of publication
Document Type
- Lecture (27)
- Article (8)
- Part of a Book (5)
- Sound (3)
- Contribution to a Periodical (2)
- Book (1)
- Article in Conference Proceedings (1)
Is part of the Bibliography
- no (47)
Keywords
- Künstliche Intelligenz (6)
- KI (4)
- Jugendhilfe (3)
- ChatGPT (2)
- Chatbot (2)
- Mensch-Maschine-Interaktion (2)
- Algorithmus (1)
- Beratung (1)
- Digitalisierung, Arbeitswelt, Vertrauen, Kommunikation (1)
- Fachkräftemangel (1)
Institute
- Sozialwesen (SW) (47)
Communicating with spoken dialogue systems (SDS) such as Apple’s Siri® and Google’s Now is becoming more and more common. We report a study that manipulates an SDS’s word use with regard to politeness. In an experiment, 58 young adults evaluated the spoken messages of our self-developed SDS as it replied to typical questions posed by university freshmen. The answers were either formulated politely or rudely. Dependent measures were both holistic measures of how students perceived the SDS as well as detailed evaluations of each single answer. Results show that participants not only evaluated the content of rude answers as being less appropriate and less pleasant than the polite answers, but also evaluated the rude system as less accurate. Lack of politeness also impacted aspects of the perceived trustworthiness of the SDS. We conclude that users of SDS expect such systems to be polite, and we then discuss some practical implications for designing SDS.
One of many ways in which spoken dialogue systems (SDS) are becoming more and more flexible is in their choice of words (e.g. alignment to the user’s vocabulary). We examined how users perceive such adaptive and non-adaptive SDS regarding trustworthiness and usability. In Experiment 1, 130 participants read out questions to an SDS that either made or did not make lexical alignment in its replies. They perceived higher cognitive demand when the SDS did not employ alignment. In Experiment 2, 135 participants listened to a conversation between a human and the same SDS in an online study. They judged the aligned SDS to have more integrity and to be more likeable. Implications for the design of SDS are discussed.
People adapt their word choice to both humans and computers. In this study, language style (elaborated vs. restricted) and perceived conversational partner (human vs. spoken dialogue system) were varied. Convergence was greater when reacting to a restricted language style. Participants preferred human partners and an elaborated language style. In line with communication accommodation theory, results suggest that considering restricted capabilities (cognitive organization) constitutes a central motive for convergence. Implications for spoken dialogue system design are discussed.
