Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text
This addresses the need for directed sentiment analysis in political text for computational social science, offering a new dataset and method that is incremental but tailored to this domain.
The paper tackles the problem of extracting directed sentiment relationships between political entities in news text, proposing a novel NLP task and constructing a manually annotated dataset from a million-scale corpus. It presents a method using a pretrained transformer with question-answering tasks, demonstrating utility by analyzing sentiments in events like the 2016 U.S. presidential election and COVID-19.
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.