human–computer interaction
PulseAugur coverage of human–computer interaction — every cluster mentioning human–computer interaction across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
Study: XAI explanation correctness impacts human understanding, but not always
A new study published on arXiv investigates the relationship between the functional correctness of explainable AI (XAI) methods and human understanding. Researchers conducted a user study with 200 participants, manipula…
-
New thesis proposes HCI framework for ethical AI in HR hiring
A new thesis explores the integration of fairness and user experience in automated machine learning (AutoML) tools specifically for human resources hiring processes. It highlights that while AutoML enhances efficiency, …
-
Smartphone data offers objective assessment for chronic disease symptoms
Researchers have developed a method to assess fatigue, sleep, and activity levels in patients with neurodegenerative and inflammatory diseases using smartphone data. This approach aims to provide a more objective and re…
-
AI-generated counterspeech can be personalized for greater impact
Researchers have developed and evaluated strategies for generating contextualized AI-powered counterspeech to combat online toxicity. Unlike generic approaches, these new methods adapt to the conversational context and …
-
Paper proposes AI system for geopolitical reflection among tech workers
A new paper proposes an AI-enabled interactive narrative system designed to foster geopolitical awareness among tech workers. The system aims to encourage critical examination of assumptions and values related to techno…
-
New protocol elicits XAI needs from stroke survivors for rehabilitation systems
Researchers have developed a novel video-based scaffolding protocol to elicit explainable AI (XAI) requirements from stroke survivors, addressing the challenges posed by acquired communication disorders. This protocol u…
-
Extended Reality proposed as mediation layer for human-robot control
A new paper proposes Extended Reality (XR) as a crucial mediation layer for situated human control in human-robot teaming. The authors argue that XR can enhance a human collaborator's ability to understand, shape, autho…
-
Chatbot verification independent of user trust, study finds
A new research paper challenges the conventional understanding of user trust in chatbots, suggesting that trust levels do not significantly impact a user's tendency to verify chatbot outputs. The study, which surveyed 1…
-
Conversational AI product advisor study reveals transparency challenges
A recent usability study explored the effectiveness of a conversational product advisor designed with transparency in mind. While participants generally found the chatbot helpful for tasks like laptop search, the built-…
-
Human-In-The-Loop AI faces scalability and fatigue challenges
This article explores the challenges of integrating humans into AI systems, a process known as Human-In-The-Loop (HITL). While humans are crucial for tasks like labeling, tuning, and validation, their involvement presen…
-
Human feedback can decrease AI trust in objective tasks, study finds
A new study published on arXiv explores how human-in-the-loop (HITL) feedback impacts user trust and perceived accuracy in AI systems. The research indicates that when tasks have objectively correct answers, user feedba…
-
New deep learning models enhance speech emotion recognition accuracy and explainability
Researchers have developed new deep learning techniques for speech emotion recognition (SER), a field crucial for advancing human-computer interaction. One study introduces a hybrid DCRF-BiLSTM model that achieves high …
-
AI believability linked to 'dimensional completeness,' not just capability
A new arXiv paper proposes that the believability of AI, particularly large language models, stems from "dimensional completeness" rather than raw capability. The authors suggest that AI agents need to express specific …
-
New AI Empathy Framework Focuses on Managing Divergence Over Time
Researchers propose a new framework for understanding empathy in AI, shifting from a focus on immediate emotional mirroring to a concept called Interpretive Error Tolerance (IET). This framework suggests empathy in exte…
-
New LLM system EduPanel evaluates educational videos with human-like reliability
Researchers have developed EduPanel, a novel three-agent LLM system designed to evaluate the pedagogical quality of educational videos. This system breaks down the evaluation process across specialized agents, providing…
-
Study: Human-AI relationships evolve through memory and turning points
A new study published on arXiv explores the development of relationships between humans and AI systems over repeated interactions. The research, which involved 24 participants interacting with a memory-augmented convers…
-
AI is more than just a tool, author argues · 4 sources tracked
A blog post argues against the common assertion that AI is merely a tool and its impact solely depends on its usage. The author contends that this perspective is overly simplistic and dismisses the inherent complexities…
-
New framework aids structured representation of Traditional Chinese Paintings
Researchers have developed VisTCP, a novel visualization framework designed to create knowledge-graph-based representations of Traditional Chinese Paintings (TCPs). This framework aims to enhance the semantic understand…
-
New research uses interaction logs to infer user intent in data analysis
Researchers have developed a method to infer user objectives during exploratory data analysis by examining provenance logs, which record detailed user interactions. By analyzing fine-grained mouse movement data, distinc…
-
Electromyography accurately predicts Rock-Paper-Scissors gestures
Researchers have developed a method for recognizing gestures using electromyography (EMG) signals, which measure muscle activity. Their study focused on the Rock-Paper-Scissors game, finding that EMG onsets can be detec…