Summary of Tailoring Generative Ai Chatbots For Multiethnic Communities in Disaster Preparedness Communication: Extending the Casa Paradigm, by Xinyan Zhao et al.
Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm
by Xinyan Zhao, Yuan Sun, Wenlin Liu, Chau-Wai Wong
First submitted to arxiv on: 12 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study develops generative artificial intelligence (GenAI) chatbots powered by GPT-4 to communicate hurricane preparedness information to diverse residents in Florida. The chatbots were designed to vary in tone formality and cultural tailoring, with the goal of improving perceptions of their friendliness and credibility among Black, Hispanic, and Caucasian residents. A between-subjects experiment was conducted with 441 participants, revealing significant influences on perceived friendliness and credibility, which in turn relate to hurricane preparedness outcomes. This study highlights the potential of GenAI chatbots for improving diverse communities’ disaster preparedness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study makes AI chatbots that help people prepare for hurricanes by talking to them about safety. The chatbots are special because they can sound different depending on who is talking to them. Scientists tested these chatbots with 441 people from different backgrounds and found out that how the chatbot sounds affects whether people trust it or not. This matters because if people trust the chatbot, they might take steps to prepare for a hurricane. The study shows that AI chatbots can help make sure more people are prepared for emergencies. |
Keywords
* Artificial intelligence * Gpt
