The interplay of complexity and subjectivity in opinionated discourse

Abstract

This paper brings together cutting-edge, quantitative corpus methodologies and discourse analysis to explore the relationship between text complexity and subjectivity as descriptive features of opinionated language. We are specifically interested in how text complexity and markers of subjectivity and argumentation interact in opinionated discourse. Our contributions include the marriage of quantitative approaches to text complexity with corpus linguistic methods for the study of subjectivity, in addition to large-scale analyses of evaluative discourse. As our corpus, we use the Simon Fraser Opinion and Comments Corpus (SOCC), which comprises approximately 10,000 opinion articles and the corresponding reader comments from the Canadian online newspaper The Globe and Mail, as well as a parallel corpus of hard news articles also sampled from The Globe and Mail. Methodologically, we combine conditional inference trees with the analysis of random forests, an ensemble learning technique, to investigate the interplay between text complexity and subjectivity. Text complexity is defined in terms of Kolmogorov complexity, that is, the complexity of a text is measured based on its description length. In this approach, texts which can be described more efficiently are considered to be linguistically less complex. Thus, Kolmogorov complexity is a measure of structural surface redundancy. Our take on subjectivity is inspired by research in evaluative language, stance and Appraisal and defined as the expression of evaluation and opinion in language. Drawing on a sentiment analysis lexicon and the literature on stance markers, a custom set of subjectivity and argumentation markers is created. The results show that complexity can be a powerful tool in the classification of text into different text types, and that stance adverbials serve as distinctive features of subjectivity in online news comments.

Kolmogorov complexity metrics in assessing L2 proficiency: An information-theoretic approach

“…In other words, if the morphology of a writing is complex enough, syntax, as compensation, might be simplified for the efficiency of communication. This result is consistent with those observed in earlier studies ( Ehret and Szmrecsanyi, 2016 , 2019 ; Ehret and Taboada, 2021 ; Sun et al, 2021 ). For example, based on the International Corpus of Learner English (ICLE), Ehret and Szmrecsanyi (2019) have noticed a statistically significant negative correlation between syntactic and morphological complexity in essays written by EFL learners with different L2 instructional exposure.…”

“…For example, based on the International Corpus of Learner English (ICLE), Ehret and Szmrecsanyi (2019) have noticed a statistically significant negative correlation between syntactic and morphological complexity in essays written by EFL learners with different L2 instructional exposure. Such a trade-off has been observed not only in L2 writing but also in other types of texts such as literary works ( Ehret and Szmrecsanyi, 2016 ), newspaper texts ( Ehret and Taboada, 2021 ), and scientific writing ( Sun et al, 2021 ).…”

“…Thus, to measure the morphological complexity, we first randomly deleted 10% of the characters before applying compression. This proportion (i.e., 10%) is commonly adopted in previous literature ( Juola, 1998 ; Sadeniemi et al, 2008 ; Ehret and Taboada, 2021 ). Then we compressed the distorted texts to determine how well or badly the compression technique handles the distortion.…”

Effects of speaker types and L1 backgrounds on the linguistic complexity of learners’ writing

“…To assess the morphological complexity, we first randomly deleted 10% (a conventional percentage employed in previous studies; see Ehret & Taboada, 2021; Juola, 1998; Sadeniemi et al., 2008) of the characters before compressing the running texts. Then the distorted texts were compressed to identify how well or badly the compression technique deals with the distortion.…”

Subjectivity of Discourse from the Philosophic Perspective

“…In example (5), Biden improved the credibility and authority of discourse by citing the FDA's and the CDC's favorable comments on the COVID-19 vaccines. If Biden had not quoted from the authorities and directly indicated his communicative intention, it would have made his opinion too subjective and made it difficult to increase the credibility of the discourse.…”