当前位置: X-MOL 学术Soc. Sci. Comput. Rev. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Using Twitter to Detect Polling Place Issue Reports on U.S. Election Days
Social Science Computer Review ( IF 3.0 ) Pub Date : 2024-08-10 , DOI: 10.1177/08944393241269420
Prathm Juneja 1 , Luciano Floridi 2, 3
Affiliation  

In this article, we analyze whether Twitter can be used to detect relative reports of issues at polling places. We use 20,322 tweets geolocated to U.S. states that match a series of keywords on the 2010, 2012, 2014, 2016, and 2018 general election days. We fine-tune BERTweet, a pre-trained language model, using a training set of 6,365 tweets labeled as issues or non-issues. We develop a model with an accuracy of 96.9% and a recall of 72.2%, and another model with an accuracy of 90.5% and a recall of 93.5%, far exceeding the performance of baseline models. Based on these results, we argue that these BERTweet-based models are promising methods for detecting reports of polling place issues on U.S. election days. We suggest that outputs from these models can be used to supplement existing voter protection efforts and to research the impact of policies, demographics, and other variables on voting access.

中文翻译:


使用 Twitter 检测美国选举日投票站问题报告



在本文中,我们分析 Twitter 是否可以用于检测投票站问题的相关报告。我们使用地理定位到美国各州的 20,322 条推文,这些推文与 2010 年、2012 年、2014 年、2016 年和 2018 年大选日的一系列关键字相匹配。我们使用包含 6,365 条标记为问题或非问题的推文的训练集对 BERTweet(一种预训练语言模型)进行微调。我们开发的一个模型的准确度为 96.9%,召回率为 72.2%,另一个模型的准确度为 90.5%,召回率为 93.5%,远远超过了基线模型的性能。基于这些结果,我们认为这些基于 BERTweet 的模型是检测美国选举日投票站问题报告的有前景的方法。我们建议,这些模型的输出可用于补充现有的选民保护工作,并研究政策、人口统计和其他变量对投票机会的影响。
更新日期:2024-08-10
down
wechat
bug