Erion Çano

PhD Student
Dept. of Control and Computer Engineering
Politecnico di Torino
Corso Duca degli Abruzzi, 24
10129, Torino, Italy

Room: Lab1
Phone: +39 011 090 7087
Email: erion.cano@polito.it

Research Resources

Pre-trained word embeddings

MischBundle - lowercased, 60B tokens, 1.7M vocab, 300d vectors. MischBundle.zip
MoodyCorpus2 - lowercased, 24B tokens, 71,590 vocab, 300d vectors. MoodyCorpus2.zip
ItemReviews - lowercased, 2.5B tokens, 82,682 vocab, 300d vectors. ItemReviews.zip
NewsBundle - lowercased, 1.3B tokens, 171,000 vocab, 300d vectors. NewsBundle.zip
TweetsBundle - lowercased, 500M tokens, 96,055 vocab, 300d vectors. TweetsBundle.zip

If using any, please cite the following article:

Çano Erion; Morisio Maurizio. Quality of Word Embeddings on Sentiment Analysis Tasks, In: Proceedings of 22nd International Conference on Natural Language & Information Systems, Springer, NLDB 2017, Liege Belgium, June 2017, pp. 332-338, DOI: 10.1007/978-3-319-59569-6_42 BibTex

MoodyLyrics4Q: A music emotion dataset of song lyrics Download
Contains 2000 songs labeled with one of the 4 categories of Russell's model based on Last.fm tags.
If using it, please cite the following article:

Çano, Erion; Morisio, Maurizio. Music Mood Dataset Creation Based on Last.fm Tags. In: Fourth International Conference on Artificial Intelligence and Applications, AIAP 2017, Vienna Austria, 27-28 May 2017, pp. 15-26, DOI:10.5121/csit.2017.70603 BibTex

MoodyLyricsPN: A music emotion dataset of song lyrics Download
Contains 5000 songs labeled as positive or negative based on Last.fm tags.
If using it, please cite the following article:

Çano, Erion; Morisio, Maurizio. Music Mood Dataset Creation Based on Last.fm Tags. In: Fourth International Conference on Artificial Intelligence and Applications, AIAP 2017, Vienna Austria, 27-28 May 2017, pp. 15-26, DOI:10.5121/csit.2017.70603 BibTex

MoodyCorpus: A text set of 90 million tokens from English song lyrics Download
If using it, please cite the following article:

Çano Erion; Morisio Maurizio. Quality of Word Embeddings on Sentiment Analysis Tasks, In: Proceedings of 22nd International Conference on Natural Language & Information Systems, Springer, NLDB 2017, Liege Belgium, June 2017, pp. 332-338, DOI: 10.1007/978-3-319-59569-6_42 BibTex

MoodyLyrics: A music emotion dataset of song lyrics Download
Contains 2595 songs annotated in 4 quadrants of Russell's model based on text.
If using it, please cite the following article:

Çano, Erion; Morisio, Maurizio. MoodyLyrics: A Sentiment Annotated Lyrics Dataset, In: Proceedings of International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence, ACM, ISMSI 2017, Hong Kong, March 2017, pp. 118-124, DOI: 10.1145/3059336.3059340. BibTex