What's in a category? A new approach to Discourse Role Analysis

When Corporations Are People: Agent Talk and the Development of Organizational Actorhood, 1890–1934

“…Recently, sociologists interested in studying the changing cultural meanings associated with categories of actors have drawn upon automated, computational tools to analyze discourse across larger amounts of text and over longer historical periods than what was previously possible. Yet, for the most part, these methods have drawn upon co-occurrence in documents or paragraphs, rather than the close, semantic parsing of sentences that, in the tradition of Mohr, connects subjects directly to their actions and that can differentiate between passive and active subjects (but see Goldenstein and Poschmann 2019; Stuhler 2021).…”

“…Yet, as Franzosi noted, the study of agency requires attention to what actors do , which, in turn, requires linking entities to their actions and to the semantic structure in which action takes place. The use of automated tools for semantic or dependency parsing remains relatively rare in sociology, though recently scholars are demonstrating the method's applicability to a range of sociological questions (Goldenstein and Poschmann 2019; Mohr et al 2013; Stuhler 2021). In this paper, I argue that we can use these tools, in combination with others, to revisit the question Franzosi and colleagues raised about the measure of agency in text: that is, how semantic parsing tools can provide a measure of attributions of agency, a concept often at the center of theoretical debates but seldom explicitly measured (Franzosi et al 2012:4).…”

Who Does What to Whom? Making Text Parsers Work for Sociological Inquiry

“…In this framework, the concepts we conventionally use in our descriptions of social structures – actors, interactions, relationships, roles, and attributes, to name a few – become measurable in text. To this end, section 5.1 analyzed interactions between gendered characters; section 5.2 analyzed the construction of “us” as an actor in political rhetoric; and elsewhere, it was recently shown that a similar approach can be used to measure roles in textual data (Stuhler 2021). Not least, this paper is therefore an attempt to provide tools and contours for what could become a new research program.…”

“…Dependency parsers hold great promise for sociological inquiry because they have the potential to extract semantically rich relations from textual data. However, within sociology, only few have made use of this opportunity (Stuhler 2021; Goldenstein and Poschmann 2019; Mohr et al 2013; in political science, see van Atteveldt, Kleinnijenhuis and Ruigrok 2008; van Atteveldt et al 2017). My ambition here is first, to identify and explicate some of the intricacies involved in making dependency parsers work for sociological inquiry; second, to provide a framework and associated software that overcomes these problems; and third, to showcase the potential of this framework in empirical analyses.…”

“…The syntactic relations derivable via dependency parsing can provide a basis for establishing semantic ones. They are, however, too fine-grained to be of much immediate use to sociologists, who usually have little regard for categories such as “appositional modifier” or “open clausal complement.” The few sociology papers that have used parsers have left this distinction largely unacknowledged (Goldenstein and Poschmann 2019; Mohr et al 2013; for the same point of criticism, see Monroe 2019; though see Stuhler 2021). Making dependency parsers work for sociological inquiry requires us to recognize and address this mismatch.…”