High-coverage and high-precision lexica of terms annotated with emotion scores for English and Italian.
Switch branches/tags
Nothing to show
Clone or download
Latest commit c9da5ec Oct 10, 2018
Failed to load latest commit information.
DepecheMood++ Last changes to DM++ Oct 10, 2018
DepecheMood DM Original version Oct 10, 2018
README.md Last changes to DM++ Oct 10, 2018


DepecheMood Emotion Lexica

This repository contains the various versions of the resource DepecheMood, a high-quality and high-coverage emotion lexicon that has been automatically derived from crowd annotated news.


This is the newest version of the lexicon. It contains two languages (English and Italian), as well as three types of word representations (token, lemma and lemma#PoS). If you use DepecheMood++, please cite the following publication:

Araque, O., Gatti, L., Staiano, J., and Guerini, M. (2018) "DepecheMood++: a Bilingual Emotion Lexicon Built Through Simple Yet Powerful Techniques". ArXiv preprint is available at https://arxiv.org/abs/1810.03660


The original DepecheMood lexicon released in 2014, English only. If you use this version, please cite the following publication:

Staiano, J., & Guerini, M. (2014). "DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News". Proceedings of ACL-2014. Paper available at http://www.anthology.aclweb.org/P/P14/P14-2070.pdf


  title={Depeche Mood: a Lexicon for Emotion Analysis from Crowd Annotated News},
  author={Staiano, Jacopo and Guerini, Marco},
  booktitle={Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},


If you want to play with it, we also have an online DEMO to analyze the emotions evoked by a text: www.depechemood.eu Currently, this demo uses the 2014. We will update it soon.


This resource can be used for research purposes. Please cite the publications above if you use it.