The aim of this thesis is to investigate linguistic features characterizing individuals with eating disorders (EDs) by employing Natural Language Processing (NLP) methodologies. Given the limited research in the field, particularly on EDs other than Anorexia Nervosa (AN) and in languages other than English, this study specifically focuses on written productions in Italian of two different subgroups of EDs: Anorexia Nervosa and Bulimia Nervosa (BN). Data were collected from online forums and a third group was included as a control. By adopting a multidisciplinary approach, the research integrates NLP techniques and tools, such as Sentiment Analysis, Emotion Detection, Topic Modelling, and Frame Semantic Parsing, with a variety of descriptive statistics and the LIWC analysis tool. While further research is needed for a deeper understanding of linguistic markers specific to each ED, preliminary findings reveal distinct patterns in language use across the three groups, highlighting variations in emotional expression, linguistic density, and topic framing

The aim of this thesis is to investigate linguistic features characterizing individuals with eating disorders (EDs) by employing Natural Language Processing (NLP) methodologies. Given the limited research in the field, particularly on EDs other than Anorexia Nervosa (AN) and in languages other than English, this study specifically focuses on written productions in Italian of two different subgroups of EDs: Anorexia Nervosa and Bulimia Nervosa (BN). Data were collected from online forums and a third group was included as a control. By adopting a multidisciplinary approach, the research integrates NLP techniques and tools, such as Sentiment Analysis, Emotion Detection, Topic Modelling, and Frame Semantic Parsing, with a variety of descriptive statistics and the LIWC analysis tool. While further research is needed for a deeper understanding of linguistic markers specific to each ED, preliminary findings reveal distinct patterns in language use across the three groups, highlighting variations in emotional expression, linguistic density, and topic framing

Language and Eating Disorders: Investigating linguistic features of Anorexia and Bulimia Nervosa in Italian online forums through NLP techniques

ALIMENTI, VALENTINA
2023/2024

Abstract

The aim of this thesis is to investigate linguistic features characterizing individuals with eating disorders (EDs) by employing Natural Language Processing (NLP) methodologies. Given the limited research in the field, particularly on EDs other than Anorexia Nervosa (AN) and in languages other than English, this study specifically focuses on written productions in Italian of two different subgroups of EDs: Anorexia Nervosa and Bulimia Nervosa (BN). Data were collected from online forums and a third group was included as a control. By adopting a multidisciplinary approach, the research integrates NLP techniques and tools, such as Sentiment Analysis, Emotion Detection, Topic Modelling, and Frame Semantic Parsing, with a variety of descriptive statistics and the LIWC analysis tool. While further research is needed for a deeper understanding of linguistic markers specific to each ED, preliminary findings reveal distinct patterns in language use across the three groups, highlighting variations in emotional expression, linguistic density, and topic framing
2023
Language and Eating Disorders: Investigating linguistic features of Anorexia and Bulimia Nervosa in Italian online forums through NLP techniques
The aim of this thesis is to investigate linguistic features characterizing individuals with eating disorders (EDs) by employing Natural Language Processing (NLP) methodologies. Given the limited research in the field, particularly on EDs other than Anorexia Nervosa (AN) and in languages other than English, this study specifically focuses on written productions in Italian of two different subgroups of EDs: Anorexia Nervosa and Bulimia Nervosa (BN). Data were collected from online forums and a third group was included as a control. By adopting a multidisciplinary approach, the research integrates NLP techniques and tools, such as Sentiment Analysis, Emotion Detection, Topic Modelling, and Frame Semantic Parsing, with a variety of descriptive statistics and the LIWC analysis tool. While further research is needed for a deeper understanding of linguistic markers specific to each ED, preliminary findings reveal distinct patterns in language use across the three groups, highlighting variations in emotional expression, linguistic density, and topic framing
File in questo prodotto:
File Dimensione Formato  
Alimenti_528770_tesi.pdf

accesso aperto

Dimensione 9.07 MB
Formato Adobe PDF
9.07 MB Adobe PDF Visualizza/Apri

È consentito all'utente scaricare e condividere i documenti disponibili a testo pieno in UNITESI UNIPV nel rispetto della licenza Creative Commons del tipo CC BY NC ND.
Per maggiori informazioni e per verifiche sull'eventuale disponibilità del file scrivere a: unitesi@unipv.it.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14239/27788