Abitbol Jacob Levy, Morales Alfredo J
GRYZZLY SAS, 69003 Lyon, France.
MIT Media Lab, Cambridge, MA 02139, USA.
Entropy (Basel). 2021 Jun 19;23(6):780. doi: 10.3390/e23060780.
Stratifying behaviors based on demographics and socioeconomic status is crucial for political and economic planning. Traditional methods to gather income and demographic information, like national censuses, require costly large-scale surveys both in terms of the financial and the organizational resources needed for their successful collection. In this study, we use data from social media to expose how behavioral patterns in different socioeconomic groups can be used to infer an individual's income. In particular, we look at the way people explore cities and use topics of conversation online as a means of inferring individual socioeconomic status. Privacy is preserved by using anonymized data, and abstracting human mobility and online conversation topics as aggregated high-dimensional vectors. We show that mobility and hashtag activity are good predictors of income and that the highest and lowest socioeconomic quantiles have the most differentiated behavior across groups.
根据人口统计学和社会经济地位对行为进行分层对于政治和经济规划至关重要。传统的收集收入和人口统计信息的方法，如全国人口普查，在成功收集所需的财政和组织资源方面都需要成本高昂的大规模调查。在本研究中，我们使用社交媒体数据来揭示不同社会经济群体的行为模式如何用于推断个人收入。特别是，我们研究人们探索城市的方式以及将在线对话主题作为推断个人社会经济地位的一种手段。通过使用匿名数据以及将人类流动性和在线对话主题抽象为聚合的高维向量来保护隐私。我们表明，流动性和主题标签活动是收入的良好预测指标，并且社会经济最高和最低分位数在各群体之间具有最明显不同的行为。
