@inproceedings{8aaf0bb3be73475dabba93eac9906f4d,
title = "Using Noisy Self-Reports to Predict Twitter User Demographics",
abstract = "Computational social science studies often contextualize content analysis within standard demographics. Since demographics are unavailable on many social media platforms (e.g. Twitter), numerous studies have inferred demographics automatically. Despite many studies presenting proof-of-concept inference of race and ethnicity, training of practical systems remains elusive since there are few annotated datasets. Existing datasets are small, inaccurate, or fail to cover the four most common racial and ethnic groups in the United States. We present a method to identify self-reports of race and ethnicity from Twitter prole descriptions. Despite the noise of automated supervision, our self-report datasets enable improvements in classification performance on gold standard self-report survey data. The result is a reproducible method for creating large-scale training resources for race and ethnicity.",
author = "Zach Wood-Doughty and Paiheng Xu and Xiao Liu and Mark Dredze",
note = "Publisher Copyright: {\textcopyright} SocialNLP 2021 Natural Language Processing for Social Media; 9th International Workshop on Natural Language Processing for Social Media, SocialNLP 2021 ; Conference date: 10-06-2021",
year = "2021",
language = "English (US)",
series = "SocialNLP 2021 - 9th International Workshop on Natural Language Processing for Social Media, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "123--137",
editor = "Lun-Wei Ku and Cheng-Te Li",
booktitle = "SocialNLP 2021 - 9th International Workshop on Natural Language Processing for Social Media, Proceedings of the Workshop",
}