This study proposes a qualitative analysis of self replies in Wikipedia talk pages, more precisely when the first two messages of a discussion are written by the same user. This specific pattern occurs in more than 10% of threads with two messages or more and can be explained by a number of reasons. After a first examination of the lexical specificities of second messages, we propose a seven categories typology and use it to annotate two reference samples (English and French) of 100 threads each. Finally, we analyse and compare the performance of human annotators (who reach a reasonable global efficiency) and instruction-tuned LLMs (which encounter important difficulties with several categories).

翻译：本研究对维基百科讨论页中的自我回复现象进行定性分析，具体聚焦于同一用户连续撰写讨论前两条消息的情形。该特定模式出现在超过10%的包含两条及以上消息的讨论串中，其成因具有多样性。在初步考察第二条消息的词汇特征后，我们提出包含七个类别的类型学体系，并运用该体系对英语和法语各100条讨论串的参照样本进行标注。最后，我们系统分析并比较了人工标注者（达到合理的整体标注效能）与指令微调大语言模型（在多个类别上遭遇显著困难）的表现差异。