Research published in the journal Judgment and Decision Making examined how people perceive and evaluate stories generated by artificial intelligence compared to those written by humans. The study involved 1,682 adults who each read one of six short stories, with half the sample reading AI-generated pieces created by ChatGPT and the other half reading human-authored works on similar themes.
Participants were informed whether their assigned story came from an AI system or a human writer, though researchers deliberately provided false attribution in some cases to test whether labeling influenced ratings. After reading, subjects evaluated the stories on factors including how engaging and absorbing they found them, as well as overall quality. The results revealed a notable discrepancy: stories actually written by AI received higher ratings for absorption and quality from readers, yet participants gave better ratings to stories they believed were written by humans, suggesting attribution significantly influenced perception.
Dr. Deena Skolnick Weisberg from Villanova University, a senior researcher on the project, stated that AI systems have demonstrated capability to generate stories of comparable or superior quality to human-written work. She noted that attitudes toward AI technology affected ratings, with participants holding more positive views of artificial intelligence giving higher scores to stories attributed to ChatGPT.
Additional experiments with 905 participants tasked them with distinguishing human-written stories from AI-generated ones on identical themes. Success rates were poor, with one trial yielding approximately 40 percent correct identifications—worse than random chance—and another achieving 52 percent accuracy. Researchers concluded participants generally could not reliably differentiate between the two sources, though expertise with AI systems showed correlation with better discrimination ability.
Weisberg suggested that preference for human-authored stories reflected a desire for authenticity, while noting that AI stories may have been rated more favorably due to superior readability. However, external commentary from academics raised concerns about AI’s development and deployment, questioning whether the technology’s capabilities justify its environmental and ethical costs.
Article Attribution | Read More at Article Source
Article summary produced by Claude AI