A multi-step LLM pipeline that identifies and replaces offensive or intensifying emojis in tweets reduces perceived offensiveness in human evaluation, especially for mild offenses, without large semantic loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation
A multi-step LLM pipeline that identifies and replaces offensive or intensifying emojis in tweets reduces perceived offensiveness in human evaluation, especially for mild offenses, without large semantic loss.