Unsupervised Methods to Improve Aspect-Based Sentiment Analysis in Czech



Título del documento: Unsupervised Methods to Improve Aspect-Based Sentiment Analysis in Czech
Revista: Computación y sistemas
Base de datos: PERIÓDICA
Número de sistema: 000411056
ISSN: 1405-5546
Autors: 1
1
1
1
1
Institucions: 1University of West Bohemia, Faculty of Applied Sciences, Plzen. República Checa
Any:
Període: Jul-Sep
Volum: 20
Número: 3
Paginació: 365-375
País: México
Idioma: Inglés
Tipo de documento: Artículo
Enfoque: Experimental, aplicado
Resumen en inglés We examine the effectiveness of several unsupervised methods for latent semantics discovery as features for aspect-based sentiment analysis (ABSA). We use the shared task definition from SemEval 2014. In our experiments we use labeled and unlabeled corpora within the restaurants domain for two languages: Czech and English. We show that our models improve the ABSA performance and prove that our approach is worth exploring. Moreover, we achieve new state-of-the-art results for Czech. Another important contribution of our work is that we created two new Czech corpora within the restaurant domain for the ABSA task: one labeled for supervised training, and the other (considerably larger) unlabeled for unsupervised training. The corpora are available to the research community
Disciplines Ciencias de la computación,
Literatura y lingüística
Paraules clau: Procesamiento de datos,
Lingüística aplicada,
Lingüística computacional,
Análisis de textos,
Semántica latente,
Análisis de sentimiento
Keyword: Computer science,
Literature and linguistics,
Data processing,
Applied linguistics,
Computing linguistics,
Text analysis,
Latent semantics,
Sentiment analysis
Text complet: Texto completo (Ver HTML)