Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Giorgia Meloni, Meloni o la Meloni? La codifica degli antroponimi femminili in biografie generate da ChatGPT e pubblicate su Wikipedia

View through CrossRef
L’obiettivo generale dello studio è indagare la rappresentazione linguistica delle donne all’interno di testi generati da ChatGPT, confrontandola con quella dei testi scritti da esseri umani. A questo fine esaminiamo la forma e frequenza d’uso di tre tipi di antroponimi riferiti alle donne (Giorgia Meloni, Meloni, la Meloni) attraverso un’analisi di testi biografici generati automaticamente da GPT-3.5 e pubblicati su Wikipedia. L’analisi è condotta utilizzando un corpus creato appositamente per questa indagine, che comprende biografie relative a 34 personalità femminili di rilievo. I risultati ottenuti mostrano che ci sono differenze sostanziali nel modo in cui le biografie generate da ChatGPT e quelle pubblicate su Wikipedia si riferiscono alle donne. Uno dei dati più interessanti riguarda la più bassa frequenza d’uso degli antroponimi del tipo la Meloni nelle biografie generate. Questo dato apre importanti domande sia in merito ai fattori che spiegano i dati riscontrati sia sul ruolo che i testi generati potrebbero avere in futuro sull’assetto dell’italiano contemporaneo. The goal of this study is to investigate the linguistic representation of women within ChatGPT’s generated texts as compared with that of texts written by human beings. To this end, we examine the form and frequency of use of three types of anthroponyms referring to women (Giorgia Meloni, Meloni, la Meloni) through an analysis of biographical texts automatically generated by GPT-3.5 and published on Wikipedia. The analysis is conducted using a corpus created specifically for this investigation, which includes biographies related to 34 prominent female personalities. The results obtained show that there are substantial differences in how the biographies generated by ChatGPT and those published on Wikipedia relate to women. One of the most interesting outcomes concerns the lower frequency of use of anthroponyms of the type la Meloni in the generated biographies. This finding opens important questions both about the factors explaining the data found and about the role that the generated texts might play in the future on the structure of contemporary Italian.
Title: Giorgia Meloni, Meloni o la Meloni? La codifica degli antroponimi femminili in biografie generate da ChatGPT e pubblicate su Wikipedia
Description:
L’obiettivo generale dello studio è indagare la rappresentazione linguistica delle donne all’interno di testi generati da ChatGPT, confrontandola con quella dei testi scritti da esseri umani.
A questo fine esaminiamo la forma e frequenza d’uso di tre tipi di antroponimi riferiti alle donne (Giorgia Meloni, Meloni, la Meloni) attraverso un’analisi di testi biografici generati automaticamente da GPT-3.
5 e pubblicati su Wikipedia.
L’analisi è condotta utilizzando un corpus creato appositamente per questa indagine, che comprende biografie relative a 34 personalità femminili di rilievo.
I risultati ottenuti mostrano che ci sono differenze sostanziali nel modo in cui le biografie generate da ChatGPT e quelle pubblicate su Wikipedia si riferiscono alle donne.
Uno dei dati più interessanti riguarda la più bassa frequenza d’uso degli antroponimi del tipo la Meloni nelle biografie generate.
Questo dato apre importanti domande sia in merito ai fattori che spiegano i dati riscontrati sia sul ruolo che i testi generati potrebbero avere in futuro sull’assetto dell’italiano contemporaneo.
The goal of this study is to investigate the linguistic representation of women within ChatGPT’s generated texts as compared with that of texts written by human beings.
To this end, we examine the form and frequency of use of three types of anthroponyms referring to women (Giorgia Meloni, Meloni, la Meloni) through an analysis of biographical texts automatically generated by GPT-3.
5 and published on Wikipedia.
The analysis is conducted using a corpus created specifically for this investigation, which includes biographies related to 34 prominent female personalities.
The results obtained show that there are substantial differences in how the biographies generated by ChatGPT and those published on Wikipedia relate to women.
One of the most interesting outcomes concerns the lower frequency of use of anthroponyms of the type la Meloni in the generated biographies.
This finding opens important questions both about the factors explaining the data found and about the role that the generated texts might play in the future on the structure of contemporary Italian.

Related Results

Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Abstract Introduction The exact manner in which large language models (LLMs) will be integrated into pathology is not yet fully comprehended. This study examines the accuracy, bene...
Assessment of Chat-GPT, Gemini, and Perplexity in Principle of Research Publication: A Comparative Study
Assessment of Chat-GPT, Gemini, and Perplexity in Principle of Research Publication: A Comparative Study
Abstract Introduction Many researchers utilize artificial intelligence (AI) to aid their research endeavors. This study seeks to assess and contrast the performance of three sophis...
CHATGPT ASSISTANCE ON BIOCHEMISTRY LEARNING OUTCOMES OF PRE-SERVICE TEACHERS
CHATGPT ASSISTANCE ON BIOCHEMISTRY LEARNING OUTCOMES OF PRE-SERVICE TEACHERS
This research investigates the effect of ChatGPT on the learning outcomes of pre-service biology teachers. Sampling was done by purposive sampling in class A (treated with ChatGPT)...
Wikipedia: a tool to monitor seasonal diseases trends?
Wikipedia: a tool to monitor seasonal diseases trends?
ObjectiveTo explore the interest of Wikipedia as a data source to monitorseasonal diseases trends in metropolitan France.IntroductionToday, Internet, especially Wikipedia, is an im...
Exploiting Wikipedia Semantics for Computing Word Associations
Exploiting Wikipedia Semantics for Computing Word Associations
<p><b>Semantic association computation is the process of automatically quantifying the strength of a semantic connection between two textual units based on various lexi...
Appearance of ChatGPT and English Study
Appearance of ChatGPT and English Study
The purpose of this study is to examine the definition and characteristics of ChatGPT in order to present the direction of self-directed learning to learners, and to explore the po...
Wikipedia in Vascular Surgery Medical Education: Comparative Study (Preprint)
Wikipedia in Vascular Surgery Medical Education: Comparative Study (Preprint)
BACKGROUND Medical students commonly refer to Wikipedia as their preferred online resource for medical information. The quality and readability of articles ...
User Intentions to Use ChatGPT for Self-Diagnosis and Health-Related Purposes: Cross-sectional Survey Study (Preprint)
User Intentions to Use ChatGPT for Self-Diagnosis and Health-Related Purposes: Cross-sectional Survey Study (Preprint)
BACKGROUND With the rapid advancement of artificial intelligence (AI) technologies, AI-powered chatbots, such as Chat Generative Pretrained Transformer (Cha...

Back to Top