@InProceedings{lapitan-batistanavarro-albacea:2016:WSSANLP2016,
  author    = {Lapitan, Fermin Roberto  and  Batista-Navarro, Riza Theresa  and  Albacea, Eliezer},
  title     = {Crowdsourcing-based Annotation of Emotions in Filipino and English Tweets},
  booktitle = {Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {74--82},
  abstract  = {The automatic analysis of emotions conveyed in social media content, e.g.,
	tweets, has many beneficial applications. In the Philippines, one of the most
	disaster-prone countries in the world, such methods could potentially enable
	first responders to make timely decisions despite the risk of data deluge.
	However, recognising emotions expressed in Philippine-generated tweets, which
	are mostly written in Filipino, English or a mix of both, is a non-trivial
	task. In order to facilitate the development of natural language processing
	(NLP) methods that will automate such type of analysis, we have built a corpus
	of tweets whose predominant emotions have been manually annotated by means of
	crowdsourcing. Defining measures ensuring that only high-quality annotations
	were retained, we have produced a gold standard corpus of 1,146
	emotion-labelled Filipino and English tweets. We validate the value of this
	manually produced resource by demonstrating that an automatic
	emotion-prediction method based on the use of a publicly available word-emotion
	association lexicon was unable to reproduce the labels assigned via
	crowdsourcing.
	While we are planning to make a few extensions to the corpus in the near
	future, its current version has been made publicly available in order to foster
	the development of emotion analysis methods based on advanced Filipino and
	English NLP.},
  url       = {http://aclweb.org/anthology/W16-3708}
}