@InProceedings{satthar-evans-uchyigit:2017:RANLP,
  author    = {Satthar, F.Sharmila  and  Evans, Roger  and  Uchyigit, Gulden},
  title     = {A Calibration Method for Evaluation of Sentiment Analysis},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {652--660},
  abstract  = {Sentiment analysis is the computational task of extracting sentiment from a
	text document --  for example whether it expresses a positive, negative or
	neutral opinion. Various approaches have been introduced in recent years, using
	a range of different techniques to extract sentiment information from a
	document. Measuring these methods against a gold standard dataset is a useful
	way to evaluate  such systems. However, different sentiment analysis techniques
	represent sentiment values in different ways, such as discrete categorical
	classes or continuous numerical sentiment scores. This creates a challenge for
	evaluating and comparing such systems; in particular assessing                       
	 
	numerical
	scores against datasets that use fixed classes is difficult, because the
	numerical outputs have to be mapped onto the ordered classes. This paper
	proposes a novel calibration technique that uses precision vs. recall curves to
	set class thresholds to optimize a continuous sentiment analyser's performance
	against a discrete gold standard dataset. In experiments mapping a continuous
	score onto a three-class classification of movie reviews, we show that
	calibration results in a substantial increase in f-score when compared to a
	non-calibrated mapping.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_084}
}