首页|University of Saskatchewan Reports Findings in Artificial Intelligence (Comparin g emotions in ChatGPT answers and human answers to the coding questions on Stack Overflow)
University of Saskatchewan Reports Findings in Artificial Intelligence (Comparin g emotions in ChatGPT answers and human answers to the coding questions on Stack Overflow)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning - Art ificial Intelligence is the subject of a report. According to news originating f rom Saskatoon, Canada, by NewsRx correspondents, research stated, “Recent advanc es in generative Artificial Intelligence (AI) and Natural Language Processing (N LP) have led to the development of Large Language Models (LLMs) and AI-powered c hatbots like ChatGPT, which have numerous practical applications. Notably, these models assist programmers with coding queries, debugging, solution suggestions, and providing guidance on software development tasks.” Our news journalists obtained a quote from the research from the University of S askatchewan, “Despite known issues with the accuracy of ChatGPT’s responses, its comprehensive and articulate language continues to attract frequent use. This i ndicates potential for ChatGPT to support educators and serve as a virtual tutor for students. To explore this potential, we conducted a comprehensive analysis comparing the emotional content in responses from ChatGPT and human answers to 2 000 questions sourced from Stack Overflow (SO). The emotional aspects of the ans wers were examined to understand how the emotional tone of AI responses compares to that of human responses. Our analysis revealed that ChatGPT’s answers are ge nerally more positive compared to human responses. In contrast, human answers of ten exhibit emotions such as anger and disgust. Significant differences were obs erved in emotional expressions between ChatGPT and human responses, particularly in the emotions of anger, disgust, and joy. Human responses displayed a broader emotional spectrum compared to ChatGPT, suggesting greater emotional variabilit y among humans. The findings highlight a distinct emotional divergence between C hatGPT and human responses, with ChatGPT exhibiting a more uniformly positive to ne and humans displaying a wider range of emotions.”
SaskatoonCanadaNorth and Central Ame ricaArtificial IntelligenceMachine Learning
NETL
NSTL
