In this paper we describe our approach to EVALITA 2014 SENTIment POLarity Classification (SENTIPOLC) task. We participated only in the Polarity Classification subtask. By resorting to a wide set of general–purpose features qualifying the lexical and grammatical structure of a text, automatically created ad–hoc lexicons and existing free available resources, we achieved the second best accuracy.
Cimino, A., Cresci, S., Dell’Orletta, F., & Tesconi, M. (2014). Linguistically-motivated and lexicon features for sentiment analysis of italian tweets. 4th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2014)
Written by STEFANO CRESCI
Published in
Elenco Pubblicazioni - Publications
Cerca
News
- Prof. C. Magliaro - Dr. Ermes Botte, DII, Università di Pisa, "Physics-based modelling for information engineers: a practical guide", 4-7, 14, 21 March 2025
- Dr. Andrea Ria, DII, Università di Pisa, "Pivotal role of electronics in the next generation of sensor systems", 10-13 February 2025
- Prof. Claudia Caudai, Prof. Giulio Del Corso, ISTI-CNR - Pisa, Italia, "Probabilistic Neural Networks and Uncertainty Quantification", 4,6,11,13,18 February 2025
- Dario Sabella, IEEE Senior Member - ITALY, "Edge Computing technology toward 6G: applications, open-source and role of AI", 27-30 January 2025
- Ing. Pierpaolo Dini, DII, Università di Pisa, "Model-based Design of Advanced Control and Monitoring Algorithms for Power Electronics", 20-23 January 2025
