Abstract
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.
Highlights
The objectivity of interpretive text analysis—humanistic interpretation1—has been a hot potato in the social sciences since their beginning
We focus on issues that are the substance and motivation for anxiety about objectivity in interpretive research rather than analyze how social scientists discuss objectivity or how they use the word “objectivity.” We do not develop a new theory or a definition of objectivity, but we are happy if our discussion provides some materials for philosophers who are developing such things
Our investigation of the uses of topic modeling shows that objectivity in interpretive text analysis with unsupervised learning does not amount to a mechanical elimination of the researchers’ judgments from the analysis process
Summary
The objectivity of interpretive text analysis—humanistic interpretation1—has been a hot potato in the social sciences since their beginning. The main point of this paper is to provide an account of objectivity that is sufficiently well grounded on the social scientific uses of unsupervised learning to help analyze the role and limitations of modeling in these interpretive processes. As we hope to show in this paper, the introduction of machine learning methods has led to a dislocation of established practices of interpretation in the context of social scientific text analytics This provides an opportunity to rethink many interesting issues at the core of interpretive research. This happens by enabling analysts to draw on more comprehensive materials and to uncover information about word patterns that would be inaccessible without the unsupervised method
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have