Mitigating Boredom Using An Empathetic Conversational Agent

Abstract

In spite of their ubiquity, our interactions with contemporary conversational agents (CA), such as Alexa, are still transactional in nature and lack the expressiveness of human-human communication. Conversational agents equipped with the ability to detect and address users' emotional and cognitive states could make our interactions with them more human. In this work, we investigate whether an empathetic CA can help mitigate boredom. We design a protocol in order to first elicit boredom in users, and explore strategies that attempt to mitigate their boredom with the help of two conversational agents, an empathetic agent and a non-empathetic agent, administered in a Wizard-of-Oz setting. We quantify their efficacy by measuring the effects on user mood and task performance. Our user study with 34 participants shows that the empathetic CA outperforms the non-empathetic CA with respect to modulating users' mood and performance. CCS CONCEPTS • Human-centered computing → User studies; Natural language interfaces.

Mia

“…Notably, as the capabilities of the agent are limited and the purpose is not counseling but rather motivation, we also refrain from introducing agent-MIA as a 'counselor'. On the other hand, we introduce agent-Roboto as a 'virtual assistant' as it follows the structure or style of a general informative virtual assistant adopted in other studies [61,65]. Based on these reasons, we cautiously frame the two agents differently.…”

“…The notion includes providing a service to the user as quickly and accurately as possible without the need for rapport or engagement. Studies have explored such agent dialogues interacting in a succinct manner without the agent asking much follow-up or reflection [61]. The response option a user receives is mostly closed-ended, which is an important interaction property of transactional agents.…”

Alpha Oscillations in Parietal and Parietooccipital Explaining How Boredom Matters Prospective Memory

“…One was a 10-min interval in the middle and the other was a 5-min interval before the end of the recording. Previous studies about boredom induction in vigilance and intelligent driving tasks suggested that 15–21 min were required to become bored ( Martel et al, 2014 ; Samrose et al, 2020 ). This study then selected 15–25 min (a 10-min interval in the middle) after starting to ensure that participants were bored.…”

Revolutionizing interaction: the role of artificial intelligent conversation agents in human-computer interaction

“…A study conducted by Samiha Samrose in 2020 demonstrated that conversational proxies can partially alleviate feelings of boredom. Through active detection of user boredom, research conducted by Samrose indicates that conversational agents can significantly reduce both the intensity and duration of such feelings by providing interactive engagement [11]. Furthermore, these systems have the capability to conduct an initial mental health assessment and identify potential psychological issues or stressors based on the content and patterns observed within user conversations.…”