logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-01112023-121509


Tipo di tesi
Tesi di laurea magistrale
Autore
DE CARO, MONICA
URN
etd-01112023-121509
Titolo
Investigating the problem of distinguishing between native and non-native speakers by their typed texts
Dipartimento
FILOLOGIA, LETTERATURA E LINGUISTICA
Corso di studi
INFORMATICA UMANISTICA
Relatori
relatore Esuli, Andrea
Parole chiave
  • author profiling
  • authorship analysis
  • machine learning
  • native non-native
  • native speaker
  • phonology
  • pronunciation
  • text classification
Data inizio appello
02/02/2023
Consultabilità
Non consultabile
Data di rilascio
02/02/2093
Riassunto
This thesis focuses on the differences between native and non-native speakers that emerge by the comparison of their typed texts.
The comparison is carried out by mean of machine learning, applying it to datasets composed of texts in English from both native and non-native speakers. In this context, we investigate the impact of phonological features, as they may have a positive impact on this task because they mirror some behaviours that are typical of native speakers. This study is also about some issues concerning the actual need to distinguish between natives and non-natives in contexts that are far from linguistics.
File