The democratization of deep learning in TASS 2017

  1. Manuel C. Díaz Galiano
  2. Eugenio Martínez Cámara
  3. M. Ángel García Cumbreras
  4. Manuel García Vega
  5. Julio Villena Román
Revue:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Année de publication: 2018

Número: 60

Pages: 37-44

Type: Article

D'autres publications dans: Procesamiento del lenguaje natural

Résumé

TASS 2017 has brought advances in the state-of-the-art in Sentiment Analysis in Spanish, because most of the systems submitted in 2017 were grounded on Deep Learning methods. Moreover, a new corpus of tweets written in Spanish was released, which is called InterTASS. The corpus is composed of tweets manually annotated at document level. The analysis of the results with InterTASS shows that the main challenge is the classification of tweets with a neutral opinion and those ones that do not express any opinion. Likewise, the organization exposed the project of extending InterTASS with tweets written in different versions of Spanish.

Information sur le financement

This research work is partially supported by REDES project (TIN2015-65136-C2-1-R) and SMART project (TIN2017-89517-P) from the Spanish Government, and a grant from the Fondo Europeo de Desarrollo Regional (FEDER). Eugenio Martínez Cámara was supported by the Juan de la Cierva For-mación Programme (FJCI-2016-28353) from the Spanish Government.

Financeurs

Références bibliographiques

  • Araque, O., R. Barbado, J. F. Sánchez-Rada, and C. A. Iglesias. 2017. Applying recurrent neural networks to sentiment analysis of spanish tweets. In Proceedings of TASS 2017, volume 1896 of CEUR Workshop Proceedings, Murcia, Spain, September. CEUR-WS.
  • Bradley, M. M. and P. J. Lang. 1999. Affective norms for english words (anew): Stimuli, instruction manual, and affective ratings. Technical report, Center for Research in Psychophysiology, University of Florida.
  • Cerón-Guzmán, J. A. 2017. Classier ensembles that push the state-of-the-art in sentiment analysis of spanish tweets. In Proceedings of TASS 2017.
  • García-Cumbreras, M. A., J. Villena-Román, E. Martínez-Cámara, M. C. Dı́az-Galiano, M. T. Martín-Valdivia, and L. A. Ureña López. 2016. Overview of tass 2016. In TASS 2016: Workshop on Sentiment Analysis at SEPLN, pages 13–21.
  • García-Vega, M., A. Montejo-Ráez, M. C. Dı́az-Galiano, and S. M. Jiménez-Zafra. 2017. Sinai en tass 2017: Clasificación de la polaridad de tweets integrando información de usuario. In Proceedings of TASS 2017.
  • Hurtado, L.-F., F. Pla, and J.-A. González. 2017. Elirf-upv en tass 2017: Análisis de sentimientos en twitter basado en aprendizaje profundo. In Proceedings of TASS 2017.
  • Joulin, A., E. Grave, P. Bojanowski, and T. Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759.
  • Martínez Cámara, E., M. A. García Cumbreras, J. Villena Román, and J. García Morera. 2016. TASS 2015-The evolution of the spanish opinion mining systems. Procesamiento del Lenguaje Natural, 56(0):33–40.
  • Moctezuma, D., M. Graff, S. MirandaJiménez, E. S. Tellez, A. Coronado, C. N. Sánchez, and J. Ortiz-Bejar. 2017. A genetic programming approach to sentiment analysis for twitter: Tass’17. In Proceedings of TASS 2017, volume 1896 of CEUR Workshop Proceedings, Murcia, Spain, September. CEUR-WS.
  • Molina-González, M. D., E. MartínezCámara, M.-T. Martí-Valdivia, and J. M. Perea-Ortega. 2013. Semantic orientation for polarity classification in spanish reviews. Expert Systems with Applications, 40(18):7250 – 7257.
  • Montañés Salas, R. M., R. del Hoyo Alonso, J. Vea-Murguía Merck, R. Aznar Gimeno, and F. J. Lacueva-Pérez. 2017. FastText como alternativa a la utilización de deep learning en corpus pequeños. In Proceedings of TASS 2017.
  • Moreno-Ortiz, A. and C. Pérez Hernández. 2017. Tecnolengua lingmotif at tass 2017: Spanish twitter dataset classification combining wide-coverage lexical resources and text features. In Proceedings of TASS 2017.
  • Navas-Loro, M. and V. Rodríguez-Doncel. 2017. Oeg at tass 2017: Spanish sentiment analysis of tweets at document level. In Proceedings of TASS 2017, volume 1896 of CEUR Workshop Proceedings, Murcia, Spain, September. CEUR-WS.
  • Reyes-Ortiz, J. A., F. Paniagua-Reyes, B. Priego-Sánchez, and M. Tovar. 2017. Lexfar en la competencia tass 2017: Análisis de sentimientos en twitter basado en lexicones. In Proceedings of TASS 2017, volume 1896 of CEUR Workshop Proceedings, Murcia, Spain, September. CEUR-WS.
  • Rosá, A., L. Chiruzzo, M. Etcheverry, and S. Castro. 2017. Retuyt en tass 2017: Análisis de sentimientos de tweets en español utilizando svm y cnn. In Proceedings of TASS 2017.
  • Tang, D. 2015. Sentiment-specific representation learning for document-level sentiment analysis. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, WSDM ’15, pages 447–452, New York, NY, USA. ACM.
  • Tume Fiestas, F. and M. A. Sobrevilla Cabezudo. 2017. C100tpucp at tass 2017: Word embedding experiments for aspect-based sentiment analysis in spanish tweets. In Proceedings of TASS 2017, volume 1896 of CEUR Workshop Proceedings, Murcia, Spain, September. CEURWS.
  • Villena-Román, J., J. García-Morera, M. A. García-Cumbreras, E. Martínez-Cámara, M. T. Martín-Valdivia, and L. A. Ureña López. 2015. Overview of tass 2015. In TASS 2015: Workshop on Sentiment Analysis at SEPLN, pages 13–21.
  • Villena-Román, J., J. García-Morera, S. Lana-Serrano, and J. C. GonzálezCristóbal. 2014. Tass 2013 a second step in reputation analysis in spanish. Procesamiento del Lenguaje Natural, 52(0):37–44, March.
  • Villena-Román, J., S. Lana-Serrano, E. Martínez-Cámara, and J. C. GonzálezCristóbal. 2013. Tass workshop on sentiment analysis at sepln. Procesamiento del Lenguaje Natural, 50:37–44.
  • Villena Román, J., E. Martínez Cámara, J. García Morera, and S. M. Jiménez Zafra. 2015. Tass 2014 the challenge of aspect-based sentiment analysis. Procesamiento del Lenguaje Natural, 54(0):61–68.