The Design and Construction of a Chinese Sarcasm Dataset

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 485–490 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 485 How Users React to Proactive Voice Assistant Behavior While Driving Maria Schmidt1,2, Wolfgang Minker2, Steffen Werner3 1Mercedes-Benz AG, 2Ulm University, 3Daimler Trucks North America LLC {maria.m.schmidt, steffen.s.werner}@daimler.com, wolfgang.minker@uni-ulm.de Abstract Nowadays Personal Assistants (PAs) are available in multiple environments and become increasingly popular to use via voice. Therefore, we aim to provide proactive PA suggestions to car drivers via speech. These suggestions should be neither obtrusive nor increase the drivers’ cognitive load, while enhancing user experience. To assess these factors, we conducted a usability study in which 42 participants perceive proactive voice output in a Wizard-of-Oz study in a driving simulator. Traffic density was varied during a highway drive and it included six in-car-specific use cases. The latter were presented by a proactive voice assistant and in a non-proactive control condition. We assessed the users’ subjective cognitive load and their satisfaction in different questionnaires during the interaction with both PA variants. Furthermore, we analyze the user reactions: both regarding their content and the elapsed response times to PA actions. The results show that proactive assistant behavior is rated similarly positive as non-proactive behavior. Furthermore, the participants agreed to 73.8% of proactive suggestions. In line with previous research, driving-relevant use cases receive the best ratings, here we reach 82.5% acceptance. Finally, the users reacted significantly faster to proactive PA actions, which we interpret as less cognitive load compared to non-proactive behavior. Keywords: voice assistant, proactivity, user reactions 1. Introduction These days more and more people use Personal Assis- tants (PAs) via voice, such as Google Assistant and Ama- zon Alexa at home (Mittal et al., 2015), Apple Siri and Microsoft Cortana on the smartphone (Kepuska and Bo- houta, 2018), or Mercedes-Benz MBUX Voice Assistant and BMW Intelligent Personal Assistant in the car (Braun et al., 2019). These are available on many different devices and offer convenient functionalities in different environ- ments, such as setting reminders, navigating through traffic, or sending messages to friends and colleagues. While serv- ing the users’ needs, PAs constantly collect personal data in order to personalize their services and adapt their behav- ior. Adaptation needs not only to be performed in terms of adapting to the user, but also in terms of adapting to the sit- uation, in which these assistants are used. Especially, when the user drives or is busy with another task at home (e.g., cooking), the interaction with a PA is only the secondary task. Thus, user experience designers need to focus on the user’s cognitive load in such settings, too. (Gabaude et al., 2012; Villing, 2009b; Villing, 2009a) In order to investigate how users perceive proactive voice output while driving, we conducted a Wizard of Oz study in a driving simula- tor with 42 participants. We varied traffic density during a highway drive to induce different levels of cognitive load . Furthermore, we permuted six in-car …

Content truncated to 500 words