Talking to oneself in CMC: a study of self replies in Wikipedia talk pages

TL;DR

This paper investigates self-replies in Wikipedia talk pages, analyzing their linguistic features, categorizing them, and comparing human and AI annotation performance to understand their role in online discussions.

Contribution

It introduces a typology of self-replies, applies it to English and French samples, and compares human and AI annotation effectiveness.

Findings

Self-replies occur in over 10% of threads with multiple messages.

Humans achieve reasonable annotation efficiency, while LLMs face challenges.

A seven-category typology helps classify self-replies effectively.

Abstract

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).