A two-step procedure to identify lexical elements of stance constructions in discourse from political blogs

The Brexit Blog Corpus (BBC) is a collection of texts extracted from political blogs, which, in a recent study, was annotated according to a cognitive-functional stance framework by two independent annotators (Annotator A and B) using semantic criteria (Simaki et al. 2017). The goal was to label the stance or stances taken based on the overall meaning of a set of utterances. The annotators were not instructed to identify the lexical forms that were used to express the stances. In this study, we make use of those stance labelled utterances as a springboard to approach stance-taking in text from the opposite point of view, namely from how stance is realised through language. Our aim is to provide a description of the specific lexical elements used to express six stance categories, i.e., CONTRARIETY, HYPOTHETICALITY, NECESSITY, PREDICTION, SOURCE OF KNOWLEDGE, and UNCERTAINTY. To this end, we followed a two-step experimental procedure. First, we performed a quantitative analysis of the stance labelled utterances in order to identify the lexical realisations of each stance category. Second, we carried out a meta-annotation of the data. Annotator B was instructed to single out the actual lexical forms of the constructions that triggered his semantic stance category decisions. This meta-annotation procedure made it possible for us to sift out the most salient lexical realisations of the constructions of each of the six category types on the basis of the qualitative assessments made by Annotator B. We then compared the results of the quantitative and the qualitative approaches, and we present a list of shared stance expressions for each stance category type.