Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.19007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909407883821056 |
|---|---|
| author | Tanguy, Ludovic Poudat, Céline Ho-Dac, Lydia-Mai |
| author_facet | Tanguy, Ludovic Poudat, Céline Ho-Dac, Lydia-Mai |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19007 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Talking to oneself in CMC: a study of self replies in Wikipedia talk pages Tanguy, Ludovic Poudat, Céline Ho-Dac, Lydia-Mai Computation and Language 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). |
| title | Talking to oneself in CMC: a study of self replies in Wikipedia talk pages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.19007 |