Building layered, multilingual sentiment lexicons at synset and lemma levels

fcruz — Wed, 17 Dec 2014 15:37:47 +0000

Many tasks related to sentiment analysis rely on sentiment lexicons, lexical resources containing information about the emotional implications of words (e.g., sentiment orientation of words, positive or negative). In this work, we present an automatic method for building lemma-level sentiment lexicons, which has been applied to obtain lexicons for English, Spanish and other three official languages in Spain. Our lexicons are multi-layered, allowing applications to trade off between the amount of available words and the accuracy of the estimations. Our evaluations show high accuracy values in all cases. As a previous step to the lemma-level lexicons, we have built a synset-level lexicon for English similar to SentiWordNet 3.0, one of the most used sentiment lexicons nowadays. We have made several improvements in the original SentiWordNet 3.0 building method, reflecting significantly better estimations of positivity and negativity, according to our evaluations. The resource containing all the lexicons, ML-SentiCon, is publicly available.

Autores:

Cruz, Fermín L.

Troyano, José A.

Pontes, Beatriz

Ortega, F. Javier

Tipo de publicación:

Artículo de revista

Nombre de la revista:

Expert Systems with Applications

Volumen:

Número:

ISSN:

0957-4174

Revisión por pares:

Internacional:

Editorial:

Elsevier

Publicable:

DOI:

10.1016/j.eswa.2014.04.005

URL:

URL a la publicación

Palabras claves:

Sentiment analysis

Multilingual sentiment lexicons

Spanish resources for sentiment analysis

Año de publicación:

2 014

Semantic orientation for polarity classification in Spanish reviews

emcamara — Mon, 14 Jul 2014 08:48:35 +0000

Until now most of the published methods for polarity classification have been applied to English texts, but other languages are becoming increasingly important. This paper presents a new resource for the Spanish sentiment analysis research community. We have generated a new lexicon by translating into Spanish the Bin Liu English Lexicon. In order to assess the validity of the proposed lexicon a set of experiments on a Spanish review corpus are presented. In addition, the resource presented is compared with another existing Spanish lexicon. The results show that our resource outperforms the currently available Spanish lexicon for sentiment analysis.

Autores:

Molina González, M. Dolores

Martínez Cámara, Eugenio

Martín Valdivia, M. Teresa

Perea Ortega, J. Manuel