In this paper we present a lexicon–based method for the automatic analysis of opinionated documents. We built with Nooj a Sentiment Lexicon and a grammar network of Contextual Valence Shifters and we tested them on a dataset of multi-domain customer reviews, reaching an average Precision of 74% and Recall of 97% on the document-level classification task.
A Lexicon-Based Approach to Sentiment Analysis.
PELOSI, SERENA;MAISTO, ALESSANDRO
2014
Abstract
In this paper we present a lexicon–based method for the automatic analysis of opinionated documents. We built with Nooj a Sentiment Lexicon and a grammar network of Contextual Valence Shifters and we tested them on a dataset of multi-domain customer reviews, reaching an average Precision of 74% and Recall of 97% on the document-level classification task.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.