Getting a Handle on Hansard with Python and NLTK, or How to Tame the Linguistic Picture of British Politics with NLP
Bibliographic Data
| ID | 22273152 |
|---|---|
| Authors | S N Gagarin (0000-0002-8893-5083, Moscow State Institute of International Relations, corresponding author) |
| Year | 2025 |
| Volume | 3 |
| Issue | 3 |
| Pages | 81-95 |
| Publication date | 2025-12-06 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Russian journal of cultural studies and communication (JOURNAL) |
| Journal identifiers | ISSN: 2949-6330 • E-ISSN: 2949-6330 |
| Publisher | MGIMO University (PUBLISHER • RU) |
| DOI | 10.24833/rjcsc-2024-3-3-81-95 |
| OpenAlex | W7136727900 |
| Language | EN |
| References cited | 30 |
This article proposes an optimised starter’s set of basic Python and NLTK (Natural Language Toolkit) methods that are essential to the analysis of massive textual corpora conducted as part of research investigating linguistic images of the world. The need to specify and detail these applied techniques stems from the nature and scope of the inexorable challenges confronted by contemporary cognitive linguistics and lexicology in the realm of unstructured big data analysis. Their viability and practical value are demonstrated in a series of illustrative examples where they are applied to the processing of continuous parallel diachronic corpora of Hansard that capture the discourse of both chambers of the British Parliament produced in the years 2006–2023 and jointly amounting to over a third of a billion tokens. The article suggests that the methods it outlines and classifies can be seen as forming an indispensable minimum of IT competences that is capable of delivering a substantial boost to the level of research both as regards its overall quality and its competitive edge. The proposed toolkit includes an essential set of instruments for target vocabulary processing as well as for the assessment and visualization of word and phrase frequency and collocation. The author presumes that, urged by the need to keep abreast of prevailing trends, the contemporary Russian researcher of linguistic images of the world is highly likely to find themselves compelled at some point to embrace the quantitative analysis methods made possible by combining Python and NLTK. As part of its substantial and varied range of benefits, the latter would arguably help them design and customize research protocols, adapting them with ease and versatility. Lastly and most importantly, the author suggests that Python and NLTK skills may serve as a comfortable gateway towards eventually upgrading one’s linguistic research to cutting-edge global standards of technological sophistication and marketability. English translation from the Russian text: Gagarin S. N. 2024. Getting a handle on a Hansard with Python and NLTK, or how to tame the linguistic picture of British politics with NLP. Linguistics & Polyglot Studies. 10(2). P. 125–140. DOI: https:// doi.org/10.24833/2410-2423-2024-2-39-125-140
Computational linguistics · Lexicology · Phrase · Politics · Readability · Vocabulary · Word lists by frequency · Discourse Analysis and Cultural Communication · International Relations in Latin America · Language, Communication, and Linguistic Studies
Discussion of Palestinian-Israeli Conflict in British Parliament Foreign Affairs Committee (2014)
British Parliament as Center for Making Foreign Policy Decisions during Syrian Crisis (2011—2015)
Windrush Generation in the Context of the Modern Development of Multiracial Great Britain
Ethnic/Racial Terminology as a Form of Representation
From eating cake to crashing out
At the heart and in the margins
Cock-ups and slap-downs
Strategic uses of parliamentary forms of address
Politics of Exception and Unease
The ontological threat of foreign fighters
Investigating colloquialization in the British parliamentary record in the late 19th and early 20th century
Taming the Climate? Corpus analysis of politicians' speech on climate change
| Highly cited | No |
|---|