Irony Sarcasm Analysis Corpus
ClassificationSentiment AnalysisEnglishBenchmark
Irony Sarcasm Analysis Corpus is a classification-focused benchmark dataset in English that provides 33 labeled examples distributed in TSV format.
📊 This dataset is used as an LLM benchmark. See model leaderboards →
About Irony Sarcasm Analysis Corpus
Dataset contains tweets in 4 subgroups: irony, sarcasm, regular and figurative. Requires using Twitter API in order to obtain tweets.
Details
- Task
- Classification, Sentiment Analysis
- Language
- English
- Format
- TSV
- Rows / instances
- 33
- Creator
- Ling et al.
- Year
- 2016