Abstract | ||
---|---|---|
This paper presents a novel approach to Sentiment Polarity Classification in Twitter posts, by extracting a vector of weighted nodes from the graph of WordNet. These weights are used in SentiWordNet to compute a final estimation of the polarity. Therefore, the method proposes a non-supervised solution that is domain-independent. The evaluation of a generated corpus of tweets shows that this technique is promising. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.csl.2013.04.001 | Computer Speech & Language |
Keywords | Field | DocType |
novel approach,weighted node,tweets shows,twitter post,ranked wordnet graph,sentiment polarity classification,final estimation,non-supervised solution,opinion mining,sentiment analysis | PageRank,Graph,Ranking,Information retrieval,Computer science,Sentiment analysis,WordNet | Journal |
Volume | Issue | ISSN |
28 | 1 | 0885-2308 |
Citations | PageRank | References |
40 | 1.06 | 19 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arturo Montejo-Ráez | 1 | 123 | 11.19 |
Eugenio Martínez-Cámara | 2 | 241 | 18.97 |
M. Teresa Martín-Valdivia | 3 | 138 | 5.76 |
L. Alfonso Ureña-López | 4 | 208 | 14.19 |