The SENTIment POLarity Classification task was proposed in two editions of the EVALITA campaign, namely in 2014 and 2016. Both editions were organized into three different sub-tasks:

  1. subjectivity classification
  2. polarity classification
  3. irony detection
The data for SENTIPOLC 2014 were gathered from TWITA and Senti-TUT, while for the 2016 edition the dataset was further expanded by including other data sources, such as TWitterBuonaScuola and a subset of TWITA overlapping with the dataset used for the shared task on Named Entity Recognition and Linking in Italian Tweets.



Back to TWITA