It contains over 1.3 million sarcastic/non-sarcastic comment pairs.
You can find more detailed research on this corpus and its applications in the sarcasm identification systematic review on ResearchGate . [1704.05579] A Large Self-Annotated Corpus for Sarcasm Kompus 2017 Sarba
The "Sarba" part of your query appears to be a slight misspelling or phonetic variation of "Sarcasm" or "Sarc," the primary subject of that corpus. Overview of SARC (2017) It contains over 1
Identifying sarcasm is one of the hardest tasks in AI because it requires understanding: Sarcasm often depends on what was said previously. Kompus 2017 Sarba