AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias

We present the task of identifying the emotions conveyed by the lyrics of Italian opera arias. We shape the task as a multi-class supervised problem, considering the six emotions from Parrot’s tree: love, joy, admiration, anger, sadness, and fear. We manually annotated an opera corpus with 2.5k inst...

Full description

Saved in:
Bibliographic Details
Main Authors: Shibingfeng Zhang, Francesco Fernicola, Federico Garcea, Paolo Bonora, Alberto Barrón-Cedeño
Format: Article
Language:English
Published: Accademia University Press 2022-12-01
Series:IJCoL
Online Access:https://journals.openedition.org/ijcol/1039
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850165696170819584
author Shibingfeng Zhang
Francesco Fernicola
Federico Garcea
Paolo Bonora
Alberto Barrón-Cedeño
author_facet Shibingfeng Zhang
Francesco Fernicola
Federico Garcea
Paolo Bonora
Alberto Barrón-Cedeño
author_sort Shibingfeng Zhang
collection DOAJ
description We present the task of identifying the emotions conveyed by the lyrics of Italian opera arias. We shape the task as a multi-class supervised problem, considering the six emotions from Parrot’s tree: love, joy, admiration, anger, sadness, and fear. We manually annotated an opera corpus with 2.5k instances at the verse level and experimented with different classification models and representations to identify the expressed emotions. Our best-performing models consider character 3-gram representations and reach relatively low levels of macro-averaged F1. Such performance reflects the difficulty of the task at hand, partially caused by the size and nature of the corpus: relatively short verses written in 18th-century Italian. Building on what we learned from the verse-level setting, we adopt a higher granularity and increase the size of the corpus. First, we switch from verses to arias in order to have longer and more expressive texts. Second, we construct a new corpus with 40k arias (\(\sim\) 90k verses). This new dataset contains silver data, annotated by self-learning on the basis of an ensemble of binary classifiers.We then experiment with more sophisticated representations, by learning an embedding space and using it to train new models for the identification of emotions at the aria level, obtaining a significant performance boost.
format Article
id doaj-art-3e89b2bcd55d41d5813e9fe8d1401747
institution OA Journals
issn 2499-4553
language English
publishDate 2022-12-01
publisher Accademia University Press
record_format Article
series IJCoL
spelling doaj-art-3e89b2bcd55d41d5813e9fe8d14017472025-08-20T02:21:41ZengAccademia University PressIJCoL2499-45532022-12-018210.4000/ijcol.1039AriEmozione 2.0: Identifying Emotions in Opera Verses and AriasShibingfeng ZhangFrancesco FernicolaFederico GarceaPaolo BonoraAlberto Barrón-CedeñoWe present the task of identifying the emotions conveyed by the lyrics of Italian opera arias. We shape the task as a multi-class supervised problem, considering the six emotions from Parrot’s tree: love, joy, admiration, anger, sadness, and fear. We manually annotated an opera corpus with 2.5k instances at the verse level and experimented with different classification models and representations to identify the expressed emotions. Our best-performing models consider character 3-gram representations and reach relatively low levels of macro-averaged F1. Such performance reflects the difficulty of the task at hand, partially caused by the size and nature of the corpus: relatively short verses written in 18th-century Italian. Building on what we learned from the verse-level setting, we adopt a higher granularity and increase the size of the corpus. First, we switch from verses to arias in order to have longer and more expressive texts. Second, we construct a new corpus with 40k arias (\(\sim\) 90k verses). This new dataset contains silver data, annotated by self-learning on the basis of an ensemble of binary classifiers.We then experiment with more sophisticated representations, by learning an embedding space and using it to train new models for the identification of emotions at the aria level, obtaining a significant performance boost.https://journals.openedition.org/ijcol/1039
spellingShingle Shibingfeng Zhang
Francesco Fernicola
Federico Garcea
Paolo Bonora
Alberto Barrón-Cedeño
AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
IJCoL
title AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
title_full AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
title_fullStr AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
title_full_unstemmed AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
title_short AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias
title_sort ariemozione 2 0 identifying emotions in opera verses and arias
url https://journals.openedition.org/ijcol/1039
work_keys_str_mv AT shibingfengzhang ariemozione20identifyingemotionsinoperaversesandarias
AT francescofernicola ariemozione20identifyingemotionsinoperaversesandarias
AT federicogarcea ariemozione20identifyingemotionsinoperaversesandarias
AT paolobonora ariemozione20identifyingemotionsinoperaversesandarias
AT albertobarroncedeno ariemozione20identifyingemotionsinoperaversesandarias