Usable and Acceptable Response Delays of Conversational Agents in Automotive User Interfaces

The Effects of Response Time on Older and Young Adults’ Interaction Experience with Chatbot

“…Gnewuch, Morana (39) conducted an experiment with experienced technology users in a task-focused context, and the results revealed that delayed response time diminished social presence perceptions, leading to reduction of intentions to use chatbot. The ndings were further supported by the discovery that unnaturally long delays in system response time often lead users to assume an error has occurred, while very short delays are perceived as rude, this suggested that the length of a delay, not just its presence, is crucial in shaping user perceptions (40). Hrabal, Kohrs (41) further emphasized the negative impact of delayed responses, which demonstrated that such delays can lead to negative user perceptions, as evidenced by physiological signs of irritation or stress, such as changes in skin conductance patterns.…”

Usable AI: Critical Review of Its Current Issues and Trends

“…Those guidelines included the following: "Make clear what the system can do, make clear how well the system can do what it can do, time services based on context, show contextually relevant information, match relevant social norms, mitigate social biases, support efficient invocation, support efficient dismissal, support efficient correction, scope services when in doubt, make clear why the system did what it did, remember recent interactions, learn from user behavior, update and adapt cautiously, encourage granular feedback, convey the consequences of user actions, provide global controls and notify users about changes" (Amershi et al, 2019). Another example is that of (Funk et al, 2020) who added three main guidelines for overcoming response delays in automotive user interfaces, depending on empirical data. These guidelines included "do not interrupt users while making voice input, always respond within the sweet-spot response range and inform users about possible response delays" (Funk et al, 2020).…”

“…Another example is that of (Funk et al, 2020) who added three main guidelines for overcoming response delays in automotive user interfaces, depending on empirical data. These guidelines included "do not interrupt users while making voice input, always respond within the sweet-spot response range and inform users about possible response delays" (Funk et al, 2020).…”

CUI @ Auto-UI: Exploring the Fortunate and Unfortunate Futures of Conversational Automotive User Interfaces

“…Over the last several years, there has been significant interest in the use of conversational interfaces in cars, with several publications on the topic appearing in the Automotive User Interfaces (Auto-UI) and Conversational User Interfaces (CUI) conferences [7,8,12,[17][18][19]. Despite this overlap in interest, there is yet little collaboration and communication between the Auto-UI and CUI communities.…”

“…Underpinning the work already underway at the intersection of CUI and Auto-UI, these communities share interests in multimodal interaction evaluation [10,20,24], multitasking and interruptions as interaction paradigms [5,8,11,22,23], modeling mental workload [8,15,24], and mixed-methods approaches to research ranging from physiological sensing [9,10,15] to in-the-wild observation [2,6]. We aim to bring together the shared goals and compare the different approaches of these communities, establishing a community of practice that can share resources and expertise to better understand automotive conversational user interfaces.…”