SENTIPOLC - SENTIment POLarity Classification
The task consists in automatically annotating messages from the popular microblogging platform Twitter1 with a tuple of boolean values indicating the message’s subjectivity and polarity (positive or negative). Moreover, as an innovative feature this year, we ask participants to distinguish between.
- the polarity considering the potential polarity inversion due to the use of figurative language and
- the literal polarity of the tweet, in order to include the sentiment analysis of tweets containing figurative language.
Detailed guidelines, task materials and data sets for development, training and testing will be made available on the Task Website.
Valerio Basile (INRIA Sophia Antipolis, France)
Francesco Barbieri (Universitat Pompeu Fabra, Spain)
Danilo Croce (University of Rome “Tor Vergata”, Italy)
Malvina Nissim (University of Groningen, Netherlands)
Nicole Novielli (University of Bari, Italy)
Viviana Patti (University of Torino, Italy)
(please join the group before sending emails to this address)