The task consists in classifing, given a short social media post, whether it is of positive, negative, neutral or mixed sentiment (both positive and negative).
We propose a message-level task. The dataset will include short documents taken from Twitter, although we are currently considering to include posts from other social media as well.
The training and test dataset will include ironic messages, in order to investigate the phenomenon of wrong classification of polarity in ironic messages.
We propose this task for Italian and the development of a standard sentiment corpus to promote research that will lead to a better understanding of how sentiment is conveyed in tweets and other short texts.
Detailed guidelines, task materials and data sets for development, training and testing will be made available on the Task Website.
- Valerio Basile (University of Groningen)
- Andrea Bolioli (CELI)
- Malvina Nissim (FICLIT, University of Bologna)
- Viviana Patti (University of Torino)
- Paolo Rosso (Universitat Politècnica de València)
Viviana Patti patti[at]di.unito.it