Theoretical Foundations for Digital Text Analysis

Abstract

Much of social life now takes place online, and records of online social interactions are available for social science research in the form of massive digital text archives. But cultural social science has contributed little to the development of machineassisted text analysis methods. As a result few text analysis methods have been developed that link digital text data to theories about culture and discourse. This paper attempts to lay the groundwork for development of such methods by proposing metatheoretical and theoretical foundations suitable for machineassisted semantic text analysis. Metatheoretically I draw on the work of ElderVass (2012), Kaidesoja (2013) and others to argue that digital text analysis methods ought to be (and in practice implicitly are) based on a realist constructionist ontology that treats discourses as ontologically real emergent social entities that have causal relationships with non-discursive social and cognitive processes. Theoretically I follow Feldman (2006) and many others in arguing that language is fundamentally shaped by processes of embodied cognition. Researchers developing digital text analysis techniques must theoretically account for such processes if they wish to produce algorithms that can interpret texts in ways that supplement, and not only amplify, human interpretation. I critically survey contemporary text analysis methods that implicitly share these metatheoretical and theoretical positions and discuss some ways these can be further developed with newly available software.

Cultural Cartography with Word Embeddings

“…The goal, then, is to assign each word a single vector such that the "gradedness in distributional representations correlates with gradedness in semantic phenomena" (Boleda 2020:228) . 17 This procedure of inferring a word's meaning by summarizing its (linguistic) context aligns with relational theories of culture-pioneered by John Mohr (Kirchner and Mohr 2010;Mohr 1998Mohr , 2000 Hinton 1986;Ignatow 2007Ignatow , 2016Landauer and Dumais 1997;Lizardo et al 2019;Osgood 1952;Strauss and Quinn 1997;Turner 2011;Zaromb et al 2006) .…”

Developmental Idealism in Internet Search Data

“…Certain words, phrases, and metaphors offer a window into speakers' personal cultural schemas. When these "cultural keywords" are written, spoken, or read, the beliefs upon which they are based can spread to those who are exposed to them, where it can then influence subsequent behavior (D'Andrade 2005;Franzosi 2010;Franzosi et al 2012;Ignatow 2016;Quinn 2005;Strauss 2005; see also Saussure 1964;Searle 1969).…”

Identification of Behavioral Indicators in Political Protest Music

“…201 It began with basic word counting techniques used in the 1960s, but thanks to computers, content analysis of text is still in development." 202 There are several advantages to using content-based analysis. For MISO professionals, one is the desire to conduct analysis of a foreign target audience with the luxury of remaining in the U.S. Much of the source material and supporting information can be transferred digitally.…”