APG5108 Digital language: Corpora and big data

It is commonplace to draw on large sets of data to show patterns and trends. Given the growing amount of web data, there is a pressing need for students to understand how the web can be used to interpret and generate such patterns and trends, particularly as they relate to language and communication. In this unit, students learn how the web can systematically be used to perform linguistic analysis. Focusing on digital language as involving multiple resources and modalities, the unit provides students with the knowledge and skills to compile, analyse and communicate the results of this analysis in written and spoken texts, and to employ a quantitative, qualitative or mixed approach to web data depending on their research question. Topics covered include: ethics, scraping and extracting big data, analysing web corpora, building corpora, linguistic methodologies, and using software.

As one of two new 6 credit point units on digital language, this unit can be taken as a standalone or together with digital language: users and technologies.