Abstract
Irony is characterized by a strong contrast between what is said and what is meant: this makes its detection an important task in sentiment analysis. In recent years, neural networks have given promising results in different areas, including irony detection. In this report, I describe the system used by the Aspie96 team in the IronITA competition (part of EVALITA 2018) for irony and sarcasm detection in Italian tweets.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have