A Spanish dataset for Targeted Sentiment Analysis of political headlines

  • Tomás Alves Salgueiro Instituto de Fisiología, Biología Molecular y Neurociencia, CONICET, Univ. Buenos Aires
  • Emilio Recart Zapata Instituto de Fisiología, Biología Molecular y Neurociencia - Facultad de Psicologia - Univ. Buenos Aires - CONICET
  • Damián Furman Instituto de Ciencias de la Computación, CONICET, UBA
  • Juan Manuel Perez Instituto de Ciencias de la Computación, CONICET, UBA
  • Pablo Nicolás Fernández Larrosa Instituto de Fisiología, Biología Molecular y Neurociencia, CONICET, Univ. Buenos Aires

Resumen

Subjective texts have been especially studied by several works as they can induce certain behaviours in their users. Most work focuses on user-generated texts in social networks, but some other texts also comprise opinions on  certain topics and could influence judgement criteria during political decisions. In this work, we address the task of Targeted Sentiment Analysis for the domain of news headlines, published by the main outlets during the 2019 Argentinean Presidential Elections. For this purpose, we present a polarity dataset of 1,976 headlines mentioning candidates in the 2019 elections at the target level. Preliminary experiments with state-of-the-art classification algorithms based on pre-trained linguistic models suggest that target information is helpful for this task. We make our data and pre-trained models publicly available.

Publicado
2022-12-14
Cómo citar
Salgueiro, T., Recart Zapata, E., Furman, D., Perez, J., & Fernández Larrosa, P. (2022). A Spanish dataset for Targeted Sentiment Analysis of political headlines. Memorias De Las JAIIO, 8(2), 92-97. Recuperado a partir de https://publicaciones.sadio.org.ar/index.php/JAIIO/article/view/269
Sección
ASAI - Simposio Argentino de Inteligencia Artificial

Artículos más leídos del mismo autor/a