The paper describes our submission to the task 2 of Sentiment Polarity Classification in Italian Tweets at Evalita 2016. Our approach is based on a convolutional neural network that exploits both word embeddings and Sentiment Specific word embeddings. We also experimented a model trained with a distant supervised corpus. Our submission with Sentiment Specific word embeddings achieved the first official score.
Convolutional neural networks for sentiment analysis on Italian tweets
Sartiano D.;Alzetta C.;
2016
Abstract
The paper describes our submission to the task 2 of Sentiment Polarity Classification in Italian Tweets at Evalita 2016. Our approach is based on a convolutional neural network that exploits both word embeddings and Sentiment Specific word embeddings. We also experimented a model trained with a distant supervised corpus. Our submission with Sentiment Specific word embeddings achieved the first official score.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
paper_027.pdf
accesso aperto
Licenza:
Creative commons
Dimensione
212.79 kB
Formato
Adobe PDF
|
212.79 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
