Formally comparing topic models and human-generated qualitative coding of physician mothers’ experiences of workplace discrimination

Abstract

Differences between computationally generated and human-generated themes in unstructured text are important to understand yet difficult to assess formally. In this study, we bridge these approaches through two contributions. First, we formally compare a primarily computational approach, topic modeling, to a primarily human-driven approach, qualitative thematic coding, in an impactful context: physician mothers’ experience of workplace discrimination. Second, we compare our chosen topic model to a principled alternative topic model to make explicit study design decisions meriting consideration in future research. By formally contrasting computationally generated (i.e. topic modeling) and human-generated (i.e. thematic coding) knowledge, we shed light on issues of interest to several audiences, notably computational social scientists who wish to understand study design tradeoffs, and qualitative researchers who may wish to leverage computational methods to improve the speed and reproducibility of labor-intensive coding. Although useful in other domains, we highlight the value of fast, reproducible methods to better understand experiences of workplace discrimination.