No keyword is an island: in search of covert associations

Abstract

This paper describes how corpus-assisted discourse analysis based on keyword identification and interpretation can benefit from employing Market Basket Analysis (mba) after keyword extraction. mba is a data mining technique used originally in marketing that can reveal consistent associations between items in a shopping cart, but also between keywords in a corpus of many texts. By identifying recurring associations between keywords, we can compensate for the lack of wider context which is a major issue impeding the interpretation of isolated keywords (especially when analysing large data). To showcase the advantages of mba in ‘re-contextualising’ keywords within the discourse, we conducted a pilot study on the topic of migration, contrasting anti-system and centre-right Czech Internet media. The results show that mba is useful in identifying the dominant strategy of anti-system news portals: to weave in a confounding ideological undercurrent and connect the concept of migrants to a multitude of other topics (i.e., flooding the discourse).

When is a Crisis Really a Crisis? Using NLP and Corpus Linguistic Methods to Reveal Differences in Migration Discourse Across Czech Media

“…3) are absent from mainstream media: "the West," NATO, China, the USA, and the Czech conservative party ODS. This result supports Cvrček and Fidler's (2022) conclusions that a Czech NATO exit was a part of the anti-systemic media discourse. Several entities have a higher frequency ranking in alternative media, such as Russia(n), ISIS, Ukraine, the USA, and Africa.…”

“…Furthermore, Ukraine was among the top thirty most mentioned entities in alternative media already in 2015. A future study could thus further examine this pre-2022 invasion discourse better to understand the messaging of the prominent Kremlin-linked alternative media, similar to Cvrček and Fidler (2022). Overall, there are about twice as many unique entities in both media types during the last period (four to five in periods 1 and 2, eight and nine in period 3), pointing to a growing gap between the mainstream and alternative media types.…”