Random Walk Weighting over SentiWordNet for Sentiment Polarity Detection on Twitter
Arturo Montejo‐Ráez, Eugenio Martínez‐Cámara, María Teresa Martín Valdivia, Luís Alfonso Ureña López · 2012
This paper presents a novel approach in Sentiment Polarity Detection on Twitter posts, by extracting a vector of weighted nodes from the graph of WordNet. These weights are used on SentiWordNet to compute a final estimation of the polarity. Therefore, the method proposes a non-supervised solution that is domain-independent. The evaluation over a generated corpus of tweets shows that this technique is promising. 1