Abstract
This study proposes an experimental method to trace the historical evolution of media discourse as a means to investigate the construction of collective meaning. Based on distributional semantics theory (Harris, 1954; Firth, 1957) and critical discourse theory (Wodak and Fairclough, 1997), it explores the value of merging two techniques widely employed to investigate language and meaning in two separate fields: neural word embeddings (computational linguistics) and the discourse-historical approach (DHA; Reisigl and Wodak, 2001) (applied linguistics). As a use case, we investigate the historical changes in the semantic space of public discourse of migration in the United Kingdom, and we use the Times Digital Archive (TDA) from 1900 to 2000 as dataset. For the computational part, we use the publicly available TDA word2vec models1 (Kenter et al., 2015; Martinez-Ortiz et al., 2016); these models have been trained according to sliding time windows with the specific intention to map conceptual change. We then use DHA to triangulate the results generated by the word vector models with social and historical data to identify plausible explanations for the changes in the public debate. By bringing the focus of the analysis to the level of discourse, with this method, we aim to go beyond mapping different senses expressed by single words and to add the currently missing sociohistorical and sociolinguistic depth to the computational results. The study rests on the foundation that social changes will be reflected in changes in public discourse (Couldry, 2008). Although correlation does not prove direct causation, we argue that historical events, language, and meaning should be considered as a mutually reinforcing cycle in which the language used to describe events shapes explicit meanings, which in turn trigger other events, which again will be reflected in the public discourse.
Highlights
The emergence of unprecedented masses of digital data has brought an upsurge in Natural Language Processing (NLP) studies concerned with language and meaning
We investigate the historical changes in the semantic space of public discourse of migration in the United Kingdom, and we use the Times Digital Archive (TDA) from 1900 to 2000 as dataset
A recent survey of studies on lexical semantic change detection (i.e., Tahmasebi et al, 2018), for instance, has indicated that the “issue of interdependence between semantic changes of different words” remains largely unexplored (Tahmasebi et al, 2018, p. 42). This would be due to that fact that works on lexical semantic change based on neural word embeddings have almost exclusively investigated single words
Summary
The emergence of unprecedented masses of digital data has brought an upsurge in Natural Language Processing (NLP) studies concerned with language and meaning These studies today are mostly based on distributional semantics theory (Harris, 1954; Firth, 1957) and typically use techniques such as neural word embeddings to map different senses expressed by single words. This would be due to that fact that works on lexical semantic change based on neural word embeddings have almost exclusively investigated single words According to these studies, meaning change should on the contrary be understood as belonging to “an intricate net of word-to-word interrelation” as the focus on single words does not allow for a comprehensive view of how a given word changes meaning. This may suggest that, rather than looking at word senses separately, whole concepts or topics should be the focus of inquiry so that meaning changes are studied in the context of other words that express (or used to express) the same or related concepts
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
