Yang Hongli, Zhang Yu, Guo Jixuan
Faculty of Education, Northeast Normal University, Changchun 130024, China.
International School of Business and Finance, Sun Yat-sen University, Zhuhai 519082, China.
Behav Sci (Basel). 2025 Apr 13;15(4):518. doi: 10.3390/bs15040518.
Due to their efficiency, stability, and enhanced language comprehension and analysis capabilities, generative AIs have attracted increasing attention in the field of writing as higher-level automated writing evaluation (AWE) feedback tools. However, few studies have examined the impact of pre-service teachers using generative AI in combination with their own teaching experience to provide feedback on Chinese writing. To fill this gap, based on 1035 writing feedback texts, we examined the differences in writing feedback between 11 pre-service teachers and Erine Bot (a generative AI) and interviewed the pre-service teachers about their willingness to cooperate with generative AI. The collaborative writing feedback generated by the pre-service teachers using AI was compared with the feedback generated by the pre-service teachers and generative AI separately. We identified that, although Ernie Bot provided significantly better feedback than the pre-service teachers in three specific areas (except for language expression), and both Ernie Bot and the pre-service teachers had respective advantages in terms of writing strategy, human-computer cooperative writing feedback was significantly better than the writing feedback provided by either Ernie Bot or the pre-service teachers alone. The was true across all aspects of the feedback in terms of focus and strategy. These findings can support the training of pre-service teachers and improve the writing quality of their students via implementing AI to provide more effective writing feedback.
由于生成式人工智能具有高效性、稳定性以及更强的语言理解和分析能力，作为更高级的自动化写作评估（AWE）反馈工具，它在写作领域吸引了越来越多的关注。然而，很少有研究探讨职前教师结合自身教学经验使用生成式人工智能对中文写作提供反馈的影响。为填补这一空白，基于1035篇写作反馈文本，我们研究了11名职前教师与文生一言（一种生成式人工智能）在写作反馈上的差异，并就职前教师与生成式人工智能合作的意愿对他们进行了访谈。将职前教师使用人工智能生成的协作写作反馈与职前教师和生成式人工智能分别生成的反馈进行了比较。我们发现，尽管文生一言在三个特定领域（语言表达除外）提供的反馈明显优于职前教师，并且文生一言和职前教师在写作策略方面都有各自的优势，但人机协作写作反馈明显优于文生一言或职前教师单独提供的写作反馈。在反馈的重点和策略等所有方面都是如此。这些发现可以支持职前教师的培训，并通过实施人工智能提供更有效的写作反馈来提高其学生的写作质量。
