PSO fusion reaches 94% accuracy on television sarcasm benchmark
A PSO-fused model combining text, speech and video representations reached 94.0% accuracy on 690 labeled television-dialogue utterances in the MUStARD ...
Tag: conversational AI
Cross-sectional survey finds chatbot use widespread among Sudanese medical students
A cross-sectional survey of 2,507 Sudanese medical students found widespread chatbot use and high rates of distress, but did not ...
Research report: AI-driven virtual reality simulation for nursing de-escalation training: development, automated assessment, and pilot expert evaluation
A seven-person pilot found that AI-scored speech in a virtual-reality nursing simulation agreed with expert labels in 96.10% of 77 ...
Virtual Reality Games With AI Conversation Could Transform Speech Therapy for Children
Bulgarian researchers have built six VR serious games with integrated conversational AI and a four-level assessment framework that preliminary tests ...
When AI Is the Only Doctor in Town: Access, Not Just Prompt Skill, Divides Health Advice
A new commentary argues that for low-resource populations, healthcare access rather than prompt literacy is the primary inequality shaping whether ...
Voice assistants earn trust task by task, not as human-like friends, study finds
In-home interviews with 22 users reveal that trust in Alexa, Siri and ChatGPT voice mode is bounded, task-specific and experience-calibrated ...
Why Socially Anxious Young Adults Turn to Chatbots: New Study Maps the Path to Problematic AI Use
A new study of 1,034 Chinese young adults finds that social anxiety drives problematic chatbot use through anthropomorphism, emotional attachment, ...
Team of AI Agents Brings Live City Data to Tourism Guidance in Lisbon
A multi-agent AI system called LISBOA grounds travel and mobility answers in live Lisbon data, lifting judged quality scores by ...
Chatbots Never Forget: The Systemic Privacy Risks Hidden Inside Conversational AI
A comprehensive review warns that conversational AI agents pose systemic privacy risks, from memorized personal data and prompt injection attacks ...
AI Learns to Explain Emotions in Conversations With Structured Precision
A new generative protocol called BridgeProt achieves top accuracy and perfect structural validity in emotion-cause pair extraction by verifying each ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!