Oracles of Peace: Topic Modeling, Cultural Opportunity, and the Nobel Peace Prize, 1902–2012*

Light, Ryan; Cunningham, Jeanine

doi:10.17813/1086-671x-20-4-43

Cited by 15 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They found this sequential design enriching, as TM inductively revealed passages where certain discursive fields were present (Törnberg & Törnberg, 2016a, p. 133). Similarly, Light and Cunningham (2016) and Lindgren (2018) used a sequential two-stage approach to examine media discourse. In both studies, TM was first applied to provide an overview of the corpus.…”

Section: Sequential Designmentioning

confidence: 99%

Topic Modeling and Text Analysis for Qualitative Policy Research

Isoaho¹,

Gritsenko²,

Mäkelä³

2019

Policy Studies Journal

121

View full text Add to dashboard Cite

This paper contributes to a critical methodological discussion that has direct ramifications for policy studies: how computational methods can be concretely incorporated into existing processes of textual analysis and interpretation without compromising scientific integrity. We focus on the computational method of topic modeling and investigate how it interacts with two larger families of qualitative methods: content and classification methods characterized by interest in words as communication units and discourse and representation methods characterized by interest in the meaning of communicative acts. Based on analysis of recent academic publications that have used topic modeling for textual analysis, our findings show that different mixed-method research designs are appropriate when combining topic modeling with the two groups of methods. Our main concluding argument is that topic modeling enables scholars to apply policy theories and concepts to much larger sets of data. That said, the use of computational methods requires genuine understanding of these techniques to obtain substantially meaningful results. We encourage policy scholars to reflect carefully on methodological issues, and offer a simple heuristic to help identify and address critical points when designing a study using topic modeling.

show abstract

Section: Sequential Designmentioning

confidence: 99%

Topic Modeling and Text Analysis for Qualitative Policy Research

Isoaho¹,

Gritsenko²,

Mäkelä³

2019

Policy Studies Journal

121

View full text Add to dashboard Cite

show abstract

“…Some scholarship has turned to a dialogic approach of studying movement/opposition discourse to understand how preceding rounds of contention shape ongoing framing efforts and how different stakeholders employ strategies to shift the dominant discourse (e.g., Coy, Woehrle, & Maney, ; Esacove, ). Other scholarship has turned to a relational approach to describe the associations formed between concepts or themes within a discourse and to trace their evolution (e.g., Light, ; Light & Cunningham, ). According to framing scholars, it is in this understudied area of frame variation that answers questions about where frames come from, how they evolve, and how they are maintained can be found (see Snow, ; Snow et al, ).…”

Section: From An Ecology Of Mind To Micromobilizationmentioning

confidence: 99%

Shifting frames: Collective action framing from a dialogic and relational perspective

Lindstedt

2017

Sociology Compass

View full text Add to dashboard Cite

This article discusses (a) sustained critiques of framing theory and of collective action frames, (b) the development and implications of a dialogic and relational alternative, and (c) suggestions for how to pursue this alternative approach using mental models. Proponents of framing theory have advocated that a dialogic and relational alternative could prove fruitful in advancing sociological understanding of the variety of contexts in which social movement discourse takes place. Drawing insights from the work of several scholars, I propose what this alternative entails in terms of both theory and research.Parallel to the development of relational sociology, academics have developed discourse mapping techniques that blend network analysis with cultural analysis. I suggest that one way researchers can integrate a dialogic and relational approach into their analyses of framing is through the use of mental models. | INTRODUCTION"If men define situations as real, they are real in their consequences."- Thomas and Thomas (1928, p. 572) Sociologists have long grappled with how the "ideal" and "material" relate to one another (see Emirbayer & Mische, 1998;Hays, 1994;Somers, 2008). Motives that guide our actions and justifications that help us to make sense of them are the principal, yet most often disputed, links that join inner experiences with external circumstances (Vaisey, 2009). The opening dictum reflects the ongoing debate in sociology over the character of this relationship, which focuses on culturally defined beliefs and their ability to reshape society (see Swidler, 2008;Vaisey, 2008aVaisey, , 2008b.In the past, scholars questioned the role of culture in determining the structure of social life (Blau, 1977; Wellman & Berkowitz, 1988;White, Boorman, & Breiger, 1976). Since then, academics have continued to separate out and explore the possible intersections of culture and structure using concepts such as cultural autonomy (Alexander & Smith, 2003;Spillman, 1995), homophily (McPherson, Smith-Lovin, & Cook, 2001;Shalizi & Thomas, 2011), cultural holes (Pachucki & Breiger, 2010;Vilhena et al., 2014), and dual-process models (Lizardo et al., 2016;Vaisey & Lizardo, 2010). Despite the appeal of conflating the study of culture with the study of group affiliations, a growing body of scholarship on "culture in action" has argued that there are ample reasons to keep them analytically distinct. In social movement studies, framing theorists sought to understand the actions of individuals through bridging cultural and structural perspectives on collective behavior. In spite of its accomplishments, critics faulted the merger for being excessively voluntaristic and for failing to offer researchers with a meaningful analysis of the pre-existing cultural codes and conventions that impinge on social action (see Hart, 1996;Swidler, 1995). However, proponents have maintained that these problems can be overcome by studying the variety of contexts in which movement discourse, decisions, and actions take place (see Sno...

show abstract

“…For measurement of other concepts than frames, see for instance, the study of issue homophily by Schmidt-Petri et al (2018), word polysemy in DiMaggio et al 2013, and literary themes in Jockers and Mimno (2013). 21 See also Light and Cunningham (2016), Miller (2013), Baier and Gengnagel (2018), and Roose et al (2018) for other examples of topic modeling which accord with topic instrumentalism. correct model which properly captures the underlying thematic structure of the texts.…”

Section: Topic Realism and Topic Instrumentalismmentioning

confidence: 99%

“…Importantly, all representations produced by topic modeling-such as the topic word lists, the prevalence of topics in the materials, and possible further analyses performed on these-can be easily visualized and shared. In this vein, for instance, Light and Cunningham (2016) used network representations of correlations between topics at different times to track the thematic evolution of Nobel Peace Prize speeches. Similarly, Baier and Gengnagel (2018) employed principal component analysis to construct a two-dimensional representation of topic correlations, which they then used to analyze discursive similarities between European Research Council (ERC) grant applications.…”

Section: Objectivity Through Transparencymentioning

confidence: 99%

Humanistic interpretation and machine learning

Pääkkönen

Ylikoski

2020

Synthese

View full text Add to dashboard Cite

This paper investigates how unsupervised machine learning methods might make hermeneutic interpretive text analysis more objective in the social sciences. Through a close examination of the uses of topic modeling—a popular unsupervised approach in the social sciences—it argues that the primary way in which unsupervised learning supports interpretation is by allowing interpreters to discover unanticipated information in larger and more diverse corpora and by improving the transparency of the interpretive process. This view highlights that unsupervised modeling does not eliminate the researchers’ judgments from the process of producing evidence for social scientific theories. The paper shows this by distinguishing between two prevalent attitudes toward topic modeling, i.e., topic realism and topic instrumentalism. Under neither can modeling provide social scientific evidence without the researchers’ interpretive engagement with the original text materials. Thus the unsupervised text analysis cannot improve the objectivity of interpretation by alleviating the problem of underdetermination in interpretive debate. The paper argues that the sense in which unsupervised methods can improve objectivity is by providing researchers with the resources to justify to others that their interpretations are correct. This kind of objectivity seeks to reduce suspicions in collective debate that interpretations are the products of arbitrary processes influenced by the researchers’ idiosyncratic decisions or starting points. The paper discusses this view in relation to alternative approaches to formalizing interpretation and identifies several limitations on what unsupervised learning can be expected to achieve in terms of supporting interpretive work.

show abstract

Oracles of Peace: Topic Modeling, Cultural Opportunity, and the Nobel Peace Prize, 1902–2012*

Cited by 15 publications

References 21 publications

Topic Modeling and Text Analysis for Qualitative Policy Research

Topic Modeling and Text Analysis for Qualitative Policy Research

Shifting frames: Collective action framing from a dialogic and relational perspective

Humanistic interpretation and machine learning

Contact Info

Product

Resources

About