arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2208.04491cs.SIphysics.soc-ph
收藏

通过结合在线和离线数据改进疫苗立场检测

Improving Vaccine Stance Detection by Combining Online and Offline Data

Anique Tahir, Lu Cheng, Paras Sheth, Huan Liu

摘要:

关于COVID-19的不同意见导致了关于疫苗的各种在线话语。由于COVID-19大流行的不利影响和规模,检测疫苗立场变得尤为重要,并日益受到关注。大流行期间的沟通通常通过在线和离线来源进行,这为检测疫苗立场提供了两个互补的途径。因此,本文旨在(1)研究整合在线和离线数据对疫苗立场检测的重要性;(2)识别影响个体疫苗立场的关键在线和离线属性。我们将疫苗犹豫作为识别在线和离线因素重要性的替代模型。借助可解释的人工智能和组合分析,我们得出结论,在线和离线因素都有助于预测疫苗立场。

英文摘要:

Differing opinions about COVID-19 have led to various online discourses regarding vaccines. Due to the detrimental effects and the scale of the COVID-19 pandemic, detecting vaccine stance has become especially important and is attracting increasing attention. Communication during the pandemic is typically done via online and offline sources, which provide two complementary avenues for detecting vaccine stance. Therefore, this paper aims to (1) study the importance of integrating online and offline data to vaccine stance detection; and (2) identify the critical online and offline attributes that influence an individual's vaccine stance. We model vaccine hesitancy as a surrogate for identifying the importance of online and offline factors. With the aid of explainable AI and combinatorial analysis, we conclude that both online and offline factors help predict vaccine stance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑