Integrating Spanish lexical resources by meta-classifiers for polarity classification

Martínez‐Cámara, Eugenio; Martín–Valdivia, María Teresa; Molina-González, M. Dolores; Perea‐Ortega, José M.

doi:10.1177/0165551514535710

Cited by 14 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The iSOL is composed of 2509 positive and 5626 negative words, thus the Spanish lexicon has 8135 opinion words in total. This resource has been successfully evaluated in several corpora and the results showed that the use of an improved list of sentiment words could be considered a good strategy for unsupervised polarity classification [32][33][34].…”

Section: Sentiment Analysis On Twittermentioning

confidence: 99%

How do sentiments affect virality on Twitter?

et al. 2021

View full text Add to dashboard Cite

Virality on Twitter is catching the attention of researchers, trying to identify factors which increase or decrease the probability of retweeting. We study how terms expressing sentiments affect retweeting frequencies by means of a regression model on the number of retweets, which is specially accurate to deal with virality. We focus on the Spanish political situation during the pseudo-referendum held in Catalonia on 1 October 2017. We have found that the use of negativity in a tweet increases the probability of retweeting and that iSOL lexicon is the one that better determines the relationship between polarity and virality.

show abstract

Section: Sentiment Analysis On Twittermentioning

confidence: 99%

How do sentiments affect virality on Twitter?

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Another approach for building a monolingual SA system for a new language is based on the use of machine translation (MT) in order to translate the text into English automatically, to then apply a polarity classifier for English, yielding as a result a kind of cross-language sentiment analysis system (Balahur and Turchi, 2012b;Wan, 2009;Perea-Ortega et al, 2013;Martínez Cámara et al, 2014). It was found that text with more sentiment is harder to translate than text with less sentiment (Chen and Zhu, 2014) and that translation errors produce an increase in the sparseness of features, a fact that degrades performance (Balahur and Turchi, 2012a;.…”

Section: Multilingual Samentioning

confidence: 99%

Universal, unsupervised (rule-based), uncovered sentiment analysis

Vilares

Gómez-Rodríguez

Alonso

2017

Knowledge-Based Systems

View full text Add to dashboard Cite

We present a novel unsupervised approach for multilingual sentiment analysis driven by compositional syntax-based rules. On the one hand, we exploit some of the main advantages of unsupervised algorithms: (1) the interpretability of their output, in contrast with most supervised models, which behave as a black box and (2) their robustness across different corpora and domains. On the other hand, by introducing the concept of compositional operations and exploiting syntactic information in the form of universal dependencies, we tackle one of their main drawbacks: their rigidity on data that are structured differently depending on the language concerned. Experiments show an improvement both over existing unsupervised methods, and over state-of-the-art supervised models when evaluating outside their corpus of origin. Experiments also show how the same compositional operations can be shared across languages. The system is available at http://www.grupolys. org/software/UUUSA/.

show abstract

“…As in the previous study the results demonstrate that the combination of sentiment classification models enhances the final performance of the system. The lack of linguistic resources for sentiment analysis in Spanish was the excuse for Martínez-Cámara et al [48] to utilize a stacking architecture to classify Spanish movie reviews. The authors employ a parallel corpus in English and Spanish to enhance the results of a classifier of Spanish reviews.…”

Section: State Of the Art Of Absamentioning

confidence: 99%

Combining resources to improve unsupervised sentiment analysis at aspect-level

Jiménez-Zafra

Martín–Valdivia

Martínez‐Cámara

et al. 2015

Journal of Information Science

Self Cite

View full text Add to dashboard Cite

Every day more companies are interested in users' opinions about their products or services. Also, every day there are more users that search for reviews on the web before purchasing a product. These users and companies are not satisfied with knowing the overall sentiment of a product, they want a finer knowledge of users' opinions. Owing to this fact, more and more researchers are working on sentiment analysis at aspect-level. This paper describes an unsupervised approach for aspect-based sentiment analysis, which aims to identify the aspects of given target entities and the sentiment expressed for each aspect. We have evaluated several tasks, although perhaps the major novelty is in the classification of the aspects. We employ a lexicon-based method combining different linguistic resources and we conclude that the combination of several classifiers improves the classification significantly. In addition, a comparison with a supervised system is performed in order to determine the strengths and weakness of each of them.

show abstract

Integrating Spanish lexical resources by meta-classifiers for polarity classification

Cited by 14 publications

References 28 publications

How do sentiments affect virality on Twitter?

How do sentiments affect virality on Twitter?

Universal, unsupervised (rule-based), uncovered sentiment analysis

Combining resources to improve unsupervised sentiment analysis at aspect-level

Contact Info

Product

Resources

About