Details

Generative AI in pragmatics : assessing the accuracy of automated speech act classification in Pinter’s The birthday party
ID Todorović, Tadej (Author), ID Flogie, Andrej (Author), ID Hari, Daniel (Author)

.pdfPDF - Presentation file, Download (168,71 KB)
MD5: 71975370DB97AE968BDFF54E11D354B0
URLURL - Source URL, Visit https://journals.uni-lj.si/elope/article/view/2195 This link opens in a new window

Abstract
This study explores the feasibility of using generative AI (ChatGPT, Gemini, and DeepSeek) to automate speech act annotation in Harold Pinter's play The Birthday Party. Three chatbots - ChatGPT, Gemini, and DeepSeek - were tested under three scenarios varying in the amount of theoretical material provided. Each chatbot's output was compared to a manually annotated reference via a Python script measuring classification accuracy. Scenario 2 produced the highest accuracy overall (75-82%), while Scenario 1 underperformed, owing to incorrect reliance on external typologies, and Scenario 3 showed signs of overfitting. ChatGPT o1 emerged as the most accurate model, achieving 82% accuracy in Scenario 2. The findings suggest that GenAI chatbots can serve as valuable preliminary annotators when good prompt-engineering and well-curated theoretical material are provided. Future research could extend this methodology to more context-dependent texts, further refining prompt-engineering strategies and exploring larger linguistic corpora.

Language:English
Keywords:pragmatics, speech act analyses, ChatGPT, DeepSeek, Gemini
Work type:Article
Typology:1.01 - Original Scientific Article
Organization:FF - Faculty of Arts
Publication status:Published
Publication version:Version of Record
Publication date:01.01.2025
Year:2025
Number of pages:Str. 19-34
Numbering:Vol. 22, no. 1
PID:20.500.12556/RUL-180084 This link opens in a new window
UDC:81’33:821.111.09-2]:004.89
ISSN on article:1581-8918
DOI:10.4312/elope.22.1.19-34 This link opens in a new window
COBISS.SI-ID:241882115 This link opens in a new window
Publication date in RUL:02.03.2026
Views:237
Downloads:113
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Record is a part of a journal

Title:ELOPE : English language overseas perspectives and enquiries
Shortened title:ELOPE
Publisher:Slovensko društvo za angleške študije, Slovensko društvo za angleške študije, Znanstvena založba Filozofske fakultete Univerze v Ljubljani, Založba Univerze v Ljubljani
ISSN:1581-8918
COBISS.SI-ID:212890112 This link opens in a new window

Licences

License:CC BY-NC-SA 4.0, Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Link:http://creativecommons.org/licenses/by-nc-sa/4.0/
Description:A Creative Commons license that bans commercial use and requires the user to release any modified works under this license.

Secondary language

Language:Slovenian
Title:Generativna umetna inteligenca v pragmatiki : analiza natančnosti samodejne klasifikacije govornih dejanj v Pinterjevi drami Zabava za rojstni dan
Abstract:
Študija raziskuje smiselnost rabe generativne umetne inteligence (ChatGPT, Gemini in DeepSeek) za avtomatizacijo anotacije govornih dejanj v Pinterjevi drami Zabava za rojstni dan. Trije klepetalni roboti - ChatGPT, Gemini in DeepSeek - so bili testirani v treh scenarijih, ki so se razlikovali glede na obseg predloženega teoretičnega gradiva. Rezultati vsakega klepetalnega robota so bili primerjani z ročno anotirano različico s pomočjo Python skripte, ki je izmerila natančnost klasifikacije. Scenarij 2 je na splošno dosegel najvišjo natančnost (75-82 %), medtem ko je bil scenarij 1 zaradi neustreznega zanašanja na tuje tipologije preslab, scenarij 3 pa je kazal znake preprileganja (angl. overfitting). ChatGPT o1 se je izkazal za najnatančnejši model, saj je v scenariju 2 dosegel 82-odstotno zanesljivost. Ugotovitve kažejo, da lahko klepetalni roboti GEN-UI služijo kot koristni predhodni anotatorji, če so na voljo dobro zasnovani pozivi in dobro pripravljeno teoretično gradivo. Prihodnje raziskave bi lahko to metodologijo razširile na besedila, ki so bolj odvisna od konteksta, nadalje izpopolnile strategije inženiringa pozivov in raziskale večje jezikovne korpuse.

Keywords:pragmatika, analiza govornih dejanj, umetna inteligenca, ChatGPT, DeepSeek, Gemini

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Collection

This document is a part of these collections:
  1. ELOPE

Back