CLNov 28, 2024

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

arXiv:2411.19007v1h-index: 6
Originality Synthesis-oriented
AI Analysis

This research addresses communication patterns in online communities like Wikipedia, but it is incremental as it focuses on a specific, narrow phenomenon.

The study analyzed self-replies in Wikipedia talk pages, where the first two messages are by the same user, a pattern occurring in over 10% of threads, and found that human annotators achieved reasonable efficiency while instruction-tuned LLMs struggled with several categories.

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).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes