用ChatGPT做文献综述可行，但需精准提示词。
Exploring the Use of ChatGPT for a Systematic Literature Review: a Design-Based Research
- 以设计研究法测试ChatGPT完成33篇论文的系统综述
- 需详细准确提示词才能保证结果可靠，存在局限性
- 提出人机协作提示结构指南，适合科研新手
ChatGPT已应用于教育领域的学习、教学与研究，具备开展系统文献综述（SLR）的潜力。然而，目前关于如何使用ChatGPT进行SLR的实证研究仍有限。本研究基于一篇已发表的SLR，采用设计研究方法，使用ChatGPT对同一组33篇论文进行文献综述，通过对比分析结果，探讨：ChatGPT在多大程度上可独立完成SLR？人类研究者应如何设计提示词以提升其可靠性与有效性？研究发现，ChatGPT具备执行SLR的能力，但依赖于详细且准确的提示词输入；同时存在局限性。研究总结出若干指导原则，供研究人员在利用ChatGPT开展文献综述时参考。
原文摘要 · Abstract (English)
ChatGPT has been used in several educational contexts,including learning, teaching and research. It also has potential to conduct the systematic literature review (SLR). However, there are limited empirical studies on how to use ChatGPT in conducting a SLR. Based on a SLR published,this study used ChatGPT to conduct a SLR of the same 33 papers in a design-based approach, to see what the differences are by comparing the reviews' results,and to answer: To what extent can ChatGPT conduct SLR? What strategies can human researchers utilize to structure prompts for ChatGPT that enhance the reliability and validity of a SLR? This study found that ChatGPT could conduct a SLR. It needs detailed and accurate prompts to analyze the literature. It also has limitations. Guiding principles are summarized from this study for researchers to follow when they need to conduct SLRs using ChatGPT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。