@inproceedings{4d5f2639d8214938878ea7e2d0c7104a,
title = "EmoTweet-28: A fine-grained emotion corpus for sentiment analysis",
abstract = "This paper describes EmoTweet-28, a carefully curated corpus of 15,553 tweets annotated with 28 emotion categories for the purpose of training and evaluating machine learning models for emotion classification. EmoTweet-28 is, to date, the largest tweet corpus annotated with fine-grained emotion categories. The corpus contains annotations for four facets of emotion: valence, arousal, emotion category and emotion cues. We first used small-scale content analysis to inductively identify a set of emotion categories that characterize the emotions expressed in microblog text. We then expanded the size of the corpus using crowdsourcing. The corpus encompasses a variety of examples including explicit and implicit expressions of emotions as well as tweets containing multiple emotions. EmoTweet-28 represents an important resource to advance the development and evaluation of more emotion-sensitive systems.",
keywords = "Emotion corpus, Microblog text, Sentiment analysis",
author = "Yan, {Jasy Liew Suet} and Turtle, {Howard R.} and Liddy, {Elizabeth D.}",
year = "2016",
language = "English (US)",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "1149--1156",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Stelios Piperidis and Bente Maegaard and Joseph Mariani",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
note = "10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
}