@inproceedings{kiritchenko-mohammad-2017-best,
    title = "Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation",
    author = "Kiritchenko, Svetlana  and
      Mohammad, Saif",
    editor = "Barzilay, Regina  and
      Kan, Min-Yen",
    booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/P17-2074/",
    doi = "10.18653/v1/P17-2074",
    pages = "465--470",
    abstract = "Rating scales are a widely used method for data annotation; however, they present several challenges, such as difficulty in maintaining inter- and intra-annotator consistency. Best{--}worst scaling (BWS) is an alternative method of annotation that is claimed to produce high-quality annotations while keeping the required number of annotations similar to that of rating scales. However, the veracity of this claim has never been systematically established. Here for the first time, we set up an experiment that directly compares the rating scale method with BWS. We show that with the same total number of annotations, BWS produces significantly more reliable results than the rating scale."
}