Ressources numériques en sciences humaines et sociales OpenEdition Nos plateformes OpenEdition Books OpenEdition Journals Hypothèses Calenda Bibliothèques OpenEdition Freemium Suivez-nous
A blueprint-style architectural rendering of a statistical software interface. The image features a dark blue background with white grid lines and technical sketches. On the left, a sidebar displays file upload controls and a statistical interpretation of a $p$-value. The center contains an "Association Plot" with cross-hatched rectangular blocks of varying sizes and heights, representing Pearson residuals across different linguistic categories. A vertical legend on the far right indicates the scale for the residuals. 0

Empowering budding corpus linguists with a custom shiny app

As corpus linguists, we often grapple with the question of how to empower students who may not have extensive coding skills to design tools that fit their research needs. With this in mind, I developed a modest yet very helpful Shiny app that simplifies running [latex]\chi^2[/latex] and Fisher’s exact tests for independence while offering access to the underlying code. This blog post explores how the app was built, its assets and limitations, and reflects on pedagogical goals.

The image presents a visual metaphor for the evolving relationship between Generative AI and Corpus Linguistics, using a sleek, biomechanical version of the Ouroboros (a serpent consuming its own tail).Formed into an infinity loop ($\infty$), the serpent is rendered in brushed gold-tone scales with cyan circuit-line accents, signifying the fusion of ancient cycles with modern technology. The left loop of the infinity symbol houses floating holographic interfaces of leading AI entities, including OpenAI, Gemini, Hugging Face, and Copilot. The right loop contains the traditional foundations of linguistic study: Sketch Engine, the British National Corpus (BNC), and the International Corpus of English (ICE).The composition illustrates the "data loop" or "model collapse" theory: the process where AI models are trained on human-generated corpora, only to eventually consume and produce data that feeds back into the global digital ecosystem. 1

Corpus linguistics in the LLM era – the changing nature of language data

The emergence of Large Language Models (LLMs) has brought both opportunities and challenges to the field of corpus linguistics. These AI systems generate vast amounts of language output that often appear natural, but is this output genuinely authentic? This raises important questions for corpus linguists about the nature of linguistic data and the methods used to study it.