Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text

TL;DR

This paper introduces a new NLP task called directed sentiment extraction to identify who blames or endorses whom in news texts, supported by a large annotated dataset and a transformer-based approach, aiding social science research.

Contribution

It proposes the novel task of directed sentiment extraction in news, creates a large annotated dataset, and develops an effective transformer-based method for this purpose.

Findings

Effective transformer-based approach for directed sentiment extraction.

Application to political events reveals insights into entity relationships.

New dataset enables future interdisciplinary NLP research.

Abstract

Understanding who blames or supports whom in news text is a critical research question in computational social science. Traditional methods and datasets for sentiment analysis are, however, not suitable for the domain of political text as they do not consider the direction of sentiments expressed between entities. In this paper, we propose a novel NLP task of identifying directed sentiment relationship between political entities from a given news document, which we call directed sentiment extraction. From a million-scale news corpus, we construct a dataset of news sentences where sentiment relations of political entities are manually annotated. We present a simple but effective approach for utilizing a pretrained transformer, which infers the target class by predicting multiple question-answering tasks and combining the outcomes. We demonstrate the utility of our proposed method for social science research questions by analyzing positive and negative opinions between political entities in two major events: 2016 U.S. presidential election and COVID-19. The newly proposed problem, data, and method will facilitate future studies on interdisciplinary NLP methods and applications.