Research on the Effect of Intelligent Writing Aids in Literary Creation
Fangyan Yan
What the paper says
This study tested how intelligent writing aids change literary creation outcomes and workflows. It was done to determine whether artificial intelligence (AI) boosts efficiency and innovation without eroding style, diversity, and author control. The authors ran a three-group experiment comparing human-AI co-writing, AI-only writing, and manual writing using 135 works across varied prompts, capturing platform logs and blind ratings for innovation, diversity, satisfaction, revision rounds, and text confusion. Co-writing produced the highest innovation, diversity, and satisfaction and the most revision loops, but it also raised confusion and occasionally triggered structural templates, theme drift, and stylistic breaks; satisfaction peaked at moderate confusion and declined when iteration became excessive. This means AI tools work best as human-led collaborators: they can expand options and reduce writer's block, but creators need to exercise governance in the way of prompt structure discipline, revision limits, and style checks to protect originality and maintain a coherent voice.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.