AriEmozione: Identifying Emotions in Opera Verses

The main task of our project was to identify the emotion expressed in a verse, in the context of an aria.

Information on Subfolders

Subfolder crossvalidation
This folder contains all the models that perform 10-fold cross validation using the cv dataset and tested on the dev dataset
Subfolder test
This folder contains all the models that are trained on the merged cv and dev dataset (ariaset_train.tsv + ariaset_dev.tsv) and tested on the test set

Further indications about how to download the corpus and run the tests can be found in each subfolder.

Data and Experiments

The corpus used in this study is available here

The full batch of results generated by the code is available here

Getting the code

You can download a copy of all the files in this repository by cloning the git repository:

git clone https://github.com/TinfFoil/AriEmozione.git

Set-up and installation

Install Pandas
pip install pandas
Install Numpy
pip install numpy
Install Keras
pip install Keras
Install sklearn
pip install sklearn
Download it_core_news_sm from spaCy (necessary for the Italian tokenizer)
python -m spacy download it_core_news_sm
If you want to run fasttext models: Install fasttext
pip install fasttext
If you want to run fasttext models using pre-trained vectors: Download fasttext's Italian pre-trained vectors and save them at the right directory path
Download the pre-trained Italian vectors from https://fasttext.cc/docs/en/crawl-vectors.html
Unzip the file and save it in "D:/vec/cc.it.300.vec/cc.it.300.vec"

If you wish to know more about our project:

We have a paper based on the AriEmozione project and it was accepted at the Seventh Italian Conference on Computational Linguistics, which will be held in March 2021. You can read it here.

Citation in bib format:

@inproceedings{DBLP:conf/clic-it/FernicolaZGBB20,
  author    = {Francesco Fernicola and
               Shibingfeng Zhang and
               Federico Garcea and
               Paolo Bonora and
               Alberto Barr{\'{o}}n{-}Cede{\~{n}}o},
  editor    = {Johanna Monti and
               Felice Dell'Orletta and
               Fabio Tamburini},
  title     = {AriEmozione: Identifying Emotions in Opera Verses},
  booktitle = {Proceedings of the Seventh Italian Conference on Computational Linguistics,
               CLiC-it 2020, Bologna, Italy, March 1-3, 2021},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {2769},
  publisher = {CEUR-WS.org},
  year      = {2020},
  url       = {http://ceur-ws.org/Vol-2769/paper\_58.pdf},
}

Full citation:

Fernicola, F., Zhang, S., et al. “AriEmozione: Identifying Emotions in Opera Verses”. In: Proceedings of the Seventh Italian Conference on Computational Linguistics, CLiC-it 2020, Bologna, Italy, March 1-3, 2021. Ed. by Johanna Monti, Felice Dell’Orletta, and Fabio Tamburini. Vol. 2769. CEUR Workshop Proceedings. CEUR-WS.org,2020. url:http://ceur-ws.org/Vol-2769/paper%5C_58.pdf.