Embeddings-based detection of word use variation in Italian newspapers

We study how words are used differently in two Italian newspapers at opposite ends of the political spectrum by training embeddings on one newspaper’s corpus, updating the weights on the second one, and observing vector shifts. We run two types of analysis, one top-down, based on a preselection of f...

Full description

Saved in:
Bibliographic Details
Main Authors: Michele Cafagna, Lorenzo De Mattei, Malvina Nissim
Format: Article
Language:English
Published: Accademia University Press 2020-12-01
Series:IJCoL
Online Access:https://journals.openedition.org/ijcol/703
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109651508527104
author Michele Cafagna
Lorenzo De Mattei
Malvina Nissim
author_facet Michele Cafagna
Lorenzo De Mattei
Malvina Nissim
author_sort Michele Cafagna
collection DOAJ
description We study how words are used differently in two Italian newspapers at opposite ends of the political spectrum by training embeddings on one newspaper’s corpus, updating the weights on the second one, and observing vector shifts. We run two types of analysis, one top-down, based on a preselection of frequent words in both newspapers, and one bottom-up, on the basis of a combination of the observed shifts and relative and absolute frequency. The analysis is specific to this data, but the method can serve as a blueprint for similar studies.
format Article
id doaj-art-374211ea7c6547c09c86fed6dcc54404
institution OA Journals
issn 2499-4553
language English
publishDate 2020-12-01
publisher Accademia University Press
record_format Article
series IJCoL
spelling doaj-art-374211ea7c6547c09c86fed6dcc544042025-08-20T02:38:01ZengAccademia University PressIJCoL2499-45532020-12-016292210.4000/ijcol.703Embeddings-based detection of word use variation in Italian newspapersMichele CafagnaLorenzo De MatteiMalvina NissimWe study how words are used differently in two Italian newspapers at opposite ends of the political spectrum by training embeddings on one newspaper’s corpus, updating the weights on the second one, and observing vector shifts. We run two types of analysis, one top-down, based on a preselection of frequent words in both newspapers, and one bottom-up, on the basis of a combination of the observed shifts and relative and absolute frequency. The analysis is specific to this data, but the method can serve as a blueprint for similar studies.https://journals.openedition.org/ijcol/703
spellingShingle Michele Cafagna
Lorenzo De Mattei
Malvina Nissim
Embeddings-based detection of word use variation in Italian newspapers
IJCoL
title Embeddings-based detection of word use variation in Italian newspapers
title_full Embeddings-based detection of word use variation in Italian newspapers
title_fullStr Embeddings-based detection of word use variation in Italian newspapers
title_full_unstemmed Embeddings-based detection of word use variation in Italian newspapers
title_short Embeddings-based detection of word use variation in Italian newspapers
title_sort embeddings based detection of word use variation in italian newspapers
url https://journals.openedition.org/ijcol/703
work_keys_str_mv AT michelecafagna embeddingsbaseddetectionofwordusevariationinitaliannewspapers
AT lorenzodemattei embeddingsbaseddetectionofwordusevariationinitaliannewspapers
AT malvinanissim embeddingsbaseddetectionofwordusevariationinitaliannewspapers