Large language models have seen extraordinary growth in popularity due to
their human-like content generation capabilities. We show that these models can
also be used to successfully cluster human-generated content, with success
defined through the measures of distinctiveness and interpretability. This
success is validated by both human reviewers and ChatGPT, providing an
automated means to close the 'validation gap' that has challenged short-text
clustering. Comparing the machine and human approaches we identify the biases
inherent in each, and question the reliance on human-coding as the 'gold
standard'. We apply our methodology to Twitter bios and find characteristic
ways humans describe themselves, agreeing well with prior specialist work, but
with interesting differences characteristic of the medium used to express
identity.

大语言模型在内容生成能力方面取得了巨大的增长，本研究展示了这些模型还可以成功地对人类生成的内容进行聚类，通过独特性和可解释性两个度量标准来定义成功。该研究验证了这一成功，通过人工审阅和 ChatGPT 的比较，提供了一种自动化的方法来弥合挑战短文本聚类的 “验证差距”。比较人工和机器方法，我们确定了每种方法固有的偏见，并质疑依赖人工编码作为 “黄金标准”。我们将该方法应用于 Twitter 个人资料描述信息，并发现人类自我描述的特点方式，与先前专家工作相吻合，但也有表达身份特点的有趣差异，这与表达身份的媒介特性有关。