Search Results

Despite being prominent and ubiquitous, message-based communication is limited in nonverbally conveying emotions. Besides emoticons or stickers, messaging users continue seeking richer options for affective communication. Recent research explored ...

• 30 chat balloon animations convey basic emotios with nuanced expression.
• Animated balloons enhance affective communication (e.g., closeness) in messaging.
• Animated balloons affect chatbot likability, expressivity, and perceived ...

Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader contextual understanding, an area in which Large Language Models (LLMs) ...

• Studied user interactions with LLM-powered Conversational Voice Assistants (VAs).
• Developed a ChatGPT-powered Alexa skill to study interactions with such VAs.
• Explored varied user interaction patterns and breakdowns across diverse ...

Requirements elicitation is a crucial activity in the software product lifecycle, ensuring a clear understanding of the user needs and project goals. This process guides the design, development, and validation phases, resulting in a successful and ...

Speech Emotion Recognition (SER) aims to identify and interpret emotional states conveyed through speech signals. Originally a branch of Affective Computing research, SER has burgeoned into a commercially viable field, seamlessly integrating into various ...

Conversational AI (CAI) systems which encompass voice- and text-based assistants are on the rise and have been largely integrated into people’s everyday lives. Despite their widespread adoption, users voice concerns regarding privacy, security ...

• Review of 158 articles on privacy, security and trust in Conversational AI systems.
• Identified constructs for assessing user perceptions of privacy, security and trust.
• Insights on reliability and validity of privacy, security and ...

This paper presents an installation showcasing the basic concepts of the FANTASIA tool and the Interaction Model built around it. The tool itself can be used in a variety of ways, through the modular set of components it provides to extend the ...

This study details the technical design and evaluation of a Multimodal Learning Analytics (MMLA) system designed to enhance spoken language acquisition in language café settings. Utilizing the MMLA Model for Design and Analysis (MAMDA) framework, ...

With the improvement of computing power and the accumulation of big data, AI technology has developed rapidly. In particular, the advancement of natural language processing and machine learning technologies has provided powerful technical support for the ...

Over the past two decades, dialogue modeling has made significant strides, moving from simple rule-based responses to personalized and persuasive response generation. However, despite these advancements, the objective functions and evaluation ...

This paper provides an insight into the work in progress of an applied research project prototyping and evaluating the user acceptance of an innovative form of patient education. The prototype of the VR app combines the capabilities of immerse VR ...

The healthcare sector is increasingly utilizing bots for patient management, chronic disease management, and health advice, providing 24/7 support and immediate medical responses. The language of these bots is crucial, impacting patient comfort, ...

Evaluating conversational assistants, such as GitHub Copilot Chat, poses a significant challenge for tool builders in the domain of Software Engineering. These assistants rely on language models and chat-based user experiences, rendering their evaluation ...

Current research on conversational recommender systems (CRS) focuses mainly on single-user interactions, neglecting situations where multiple users need to receive suggestions on a shared goal. This requires a CRS to conduct a multi-party dialogue and ...

In this study, we investigate how extended reality (XR) and conversational artificial intelligence (AI) can enhance the user experience, showcasing successful implementations. We gathered data from Scopus, Science Direct, Google Scholar, and Web ...

WisCompanion is a conversational artificial intelligence (AI) platform that merges the Socratic method with ChatGPT’s advanced prompting capabilities to provide tailored emotional support for older adults. This unique combination fosters critical ...

This paper considers the application of ambient theory for smart cities to vehicles as an approach to contributing greater understanding to increasingly more aware mobile environments. A review of the research and practice literature for people ...

This paper analyses the phenomenology and epistemology of chatbots such as ChatGPT and Bard. The computational architecture underpinning these chatbots are large language models (LLMs), which are generative artificial intelligence (AI) systems ...

In this study, we explored communication breakdowns and repair strategies among 71 children aged 4-8 years while co-creating stories with a generative AI agent enabled by Large Language Models and a human partner. Analyzing approximately 1420 minutes of ...

The recent advancements in AI technology have shown the potential for chatbots to facilitate discussions. However, current chatbots mainly focus on discussion development and do not effectively synthesize idea development into solution planning. This is ...

Fair and diverse perspectives discussion, aided by reliable AI intervention, can effectively burst filter bubbles and transform undemocratic behaviors into functional democratic processes in online forums. However, the impact of AI intervention on ...