Computational Storylines: Synthesis and Analysis

Session Goals

To define a general critical text analytics methodology for crafting computational storylines
To understand core iterative processes of synthesis and analysis involved in the crafting of computational storylines
To apply computational storylines methodology to a given corpus of text

Computational storylines are crafted through iterative processes of synthesis and analysis, drawing on both quantitative and qualitative standards for methodological rigor. Quantitative breadth and precision set parameters for researcher interpretation while affirming collective and naturalistic dimensions of meaning-making. Qualitative depth and dynamism foreground ethical and reflexive engagement with complex and context-sensitive dimensions of meaning-making.
Synthesis of computational storylines must be adequately grounded in quantitatively precise selections of words. Using computational methods, a set of words central to a given set of utterances may be identified. Interpretative engagement with these words, especially as used in actual utterances in the corpus, allows researchers to ‘connect the dots’ to form summative statements with these words which capture shared process of discursive construction.
Analysis of computational storylines must be adequately grounded in quantitatively precise selections of text extracts. Computational methods may be used to identify utterances in the corpus which exemplify the meaning-making expressed by a storyline. By interpretatively engaging these statements, researchers may unpack how a given storyline may encompass plural processes of discursive construction.

(Synthesis: Two storylines) Using the computational outputs from the previous homework, select two of the derived topics. For each of the two topics, examine their (a) 30 top-scoring words, and (b) their 30 top-scoring texts. Using at least the top 5 words, construct storylines which capture key meaning-making processes in the top-scoring texts. Indicate which words in the storylines are among the top-scoring words.
(Analysis: Three extracts per storyline) For each of the constructed storylines, select three top-scoring statements to analyze in greater detail. Strategically choose statements which will capture important nuances in the meaning-making within each storyline. Qualitatively unpack the discursive processes at work in each statement, and explain how these dynamics shed light on the overarching storyline.
(Iteration: ~5 sentences) Note that the above synthesis and analysis steps do not stand on their own, but are iteratively refined in relation to each other. Analysis sheds light on complexities which need to be integrated in the synthesis of computational storylines, while synthetic statements guide the selection of appropriate extracts for detailed analysis. Briefly narrate how your synthesis and analysis steps were initially formulated and subsequently improved each other.

Antaki, C., Billig, M., Edwards, D., & Potter, J. (2003). Discourse analysis means doing analysis: A critique of six analytic shortcomings. Discourse Analysis Online, 1(1). https://extra.shu.ac.uk/daol/articles/v1/n1/a1/antaki2002002-t.html

Bryman, A. (2006). Integrating quantitative and qualitative research: How is it done? Qualitative Research, 6(1), 97-113. https://doi.org/10.1177/1468794106058877

Jacobs, T., & Tschötschel, R. (2019). Topic models meet discourse analysis: A quantitative tool for a qualitative approach. International Journal of Social Research Methodology, 22(5), 469-485. https://doi.org/10.1080/13645579.2019.1576317