Reproduce “Social and Emotional Etiquette of Chatbots: A Qualitative Approach to Understanding User Needs and Expectations” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ekaterina Svikhnushina, Pearl Pu
A qualitative study explored user desires and apprehensions regarding emotionally aware chatbots, detailing preferred emotional interaction patterns, potential application domains, and key concerns about monetary, social, and psychological harms, informing design guidelines for future conversational AI.
Key insights
- Users desire emotional intelligence in chatbots, expecting empathy, social skills, and self-regulation (trustworthiness, adaptability), with a preference for nuanced responses to negative emotions rather than simple mirroring.
- Beyond explicit emotional language, implicit markers like interjections and emojis are crucial for chatbots to subtly convey understanding and appropriately regulate interaction.
- The design of emotionally intelligent chatbots must prioritize transparency, robust security, and a clear demonstration of benevolence to address user concerns about potential monetary, social, and psychological harms.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.