@inproceedings{asahara-2019-word,
    title = "Word Familiarity Rate Estimation Using a {B}ayesian Linear Mixed Model",
    author = "Asahara, Masayuki",
    editor = "Paun, Silviu  and
      Hovy, Dirk",
    booktitle = "Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP",
    month = nov,
    year = "2019",
    address = "Hong Kong",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-5902",
    doi = "10.18653/v1/D19-5902",
    pages = "6--14",
    abstract = "This paper presents research on word familiarity rate estimation using the {`}Word List by Semantic Principles{'}. We collected rating information on 96,557 words in the {`}Word List by Semantic Principles{'} via Yahoo! crowdsourcing. We asked 3,392 subject participants to use their introspection to rate the familiarity of words based on the five perspectives of {`}KNOW{'}, {`}WRITE{'}, {`}READ{'}, {`}SPEAK{'}, and {`}LISTEN{'}, and each word was rated by at least 16 subject participants. We used Bayesian linear mixed models to estimate the word familiarity rates. We also explored the ratings with the semantic labels used in the {`}Word List by Semantic Principles{'}.",
}