WeFeelFine as Resource for Unsupervised Polarity Classification

Arturo Montejo-Ráez

Resumen


This papers shows the results obtained by a non supervised method in the task of sentiment polarity detection on micro-blogs. This method does not need of training, but it also is self-constructed from millions of publications on the web. The results show the effectiveness of the proposal, openining a new way of facing sentiment analysis in micro-blogs

Texto completo:

PDF