Towards an integrated pipeline for aspect-based sentiment analysis in various domains

• Orphée De Clercq ^[1] ; Els Lefever ^[1] ; Gilles Jacobs ^[1] ; Tijl Carpels ^[2] ; Véronique Hoste ^[1]
  1. [1] Ghent University

     Ghent University

     Arrondissement Gent, Bélgica

     
  2. [2] Hello Customer, Belgium
• Localización: 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA 2017: Proceedings of the Workshop / Alexandra Balahur Dobrescu (ed. lit.), Saif M. Mohammad (ed. lit.), Erik van der Goot (ed. lit.), 2017, ISBN 978-1-945626-95-1, págs. 136-142
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This paper presents an integrated ABSA pipeline for Dutch that has been developed and tested on qualitative user feedback coming from three domains: retail, bank- ing and human resources. The two lat- ter domains provide service-oriented data, which has not been investigated before in ABSA. By performing in-domain and cross-domain experiments the validity of our approach was investigated. We show promising results for the three ABSA sub- tasks, aspect term extraction, aspect cat- egory classification and aspect polarity classification.