Clause complexing in research-article abstracts: Comparing human- and AI-generated texts
The ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified version of Halliday’s clause-complexing framework, this study compared 50 abstracts of scientific research articles from Nature with generate...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2023-12-01
|
| Series: | ExELL (Explorations in English Language and Linguistics) |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/exell-2023-0008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576282733314048 |
|---|---|
| author | Leong Alvin Ping |
| author_facet | Leong Alvin Ping |
| author_sort | Leong Alvin Ping |
| collection | DOAJ |
| description | The ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified version of Halliday’s clause-complexing framework, this study compared 50 abstracts of scientific research articles from Nature with generated versions produced by Bard, ChatGPT, and Poe Assistant. None of the chatbots matched the original abstracts in all categories. The only chatbot that came closest was ChatGPT, but differences in the use of finite adverbial clauses and –ing elaborating clauses were detected. Incorporating distinct grammatical features in the algorithms of AI-detection tools is crucially needed to enhance the reliability of their results. A genre-based approach to detecting AI-generated content is recommended. |
| format | Article |
| id | doaj-art-6ff01cc46d2c4616bbe26b71801502fb |
| institution | Kabale University |
| issn | 2303-4858 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | ExELL (Explorations in English Language and Linguistics) |
| spelling | doaj-art-6ff01cc46d2c4616bbe26b71801502fb2025-01-31T08:34:31ZengSciendoExELL (Explorations in English Language and Linguistics)2303-48582023-12-011129913210.2478/exell-2023-0008Clause complexing in research-article abstracts: Comparing human- and AI-generated textsLeong Alvin Ping01Nanyang Technological University, SingaporeThe ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified version of Halliday’s clause-complexing framework, this study compared 50 abstracts of scientific research articles from Nature with generated versions produced by Bard, ChatGPT, and Poe Assistant. None of the chatbots matched the original abstracts in all categories. The only chatbot that came closest was ChatGPT, but differences in the use of finite adverbial clauses and –ing elaborating clauses were detected. Incorporating distinct grammatical features in the algorithms of AI-detection tools is crucially needed to enhance the reliability of their results. A genre-based approach to detecting AI-generated content is recommended.https://doi.org/10.2478/exell-2023-0008abstractsclause complexinggenerative aibardchatgptpoe assistant |
| spellingShingle | Leong Alvin Ping Clause complexing in research-article abstracts: Comparing human- and AI-generated texts ExELL (Explorations in English Language and Linguistics) abstracts clause complexing generative ai bard chatgpt poe assistant |
| title | Clause complexing in research-article abstracts: Comparing human- and AI-generated texts |
| title_full | Clause complexing in research-article abstracts: Comparing human- and AI-generated texts |
| title_fullStr | Clause complexing in research-article abstracts: Comparing human- and AI-generated texts |
| title_full_unstemmed | Clause complexing in research-article abstracts: Comparing human- and AI-generated texts |
| title_short | Clause complexing in research-article abstracts: Comparing human- and AI-generated texts |
| title_sort | clause complexing in research article abstracts comparing human and ai generated texts |
| topic | abstracts clause complexing generative ai bard chatgpt poe assistant |
| url | https://doi.org/10.2478/exell-2023-0008 |
| work_keys_str_mv | AT leongalvinping clausecomplexinginresearcharticleabstractscomparinghumanandaigeneratedtexts |