Department of Psychology, University of Turin , Turin, Italy .
Cyberpsychol Behav Soc Netw. 2018 Apr;21(4):217-228. doi: 10.1089/cyber.2017.0384.
The increasing utilization of social media provides a vast and new source of user-generated ecological data (digital traces), which can be automatically collected for research purposes. The availability of these data sets, combined with the convergence between social and computer sciences, has led researchers to develop automated methods to extract digital traces from social media and use them to predict individual psychological characteristics and behaviors. In this article, we reviewed the literature on this topic and conducted a series of meta-analyses to determine the strength of associations between digital traces and specific individual characteristics; personality, psychological well-being, and intelligence. Potential moderator effects were analyzed with respect to type of social media platform, type of digital traces examined, and study quality. Our findings indicate that digital traces from social media can be studied to assess and predict theoretically distant psychosocial characteristics with remarkable accuracy. Analysis of moderators indicated that the collection of specific types of information (i.e., user demographics), and the inclusion of different types of digital traces, could help improve the accuracy of predictions.
社交媒体的日益普及为用户生成的生态数据（数字痕迹）提供了一个广阔而新颖的来源，这些数据可以自动收集用于研究目的。这些数据集的可用性，加上社会科学和计算机科学的融合，促使研究人员开发了从社交媒体中提取数字痕迹并将其用于预测个体心理特征和行为的自动化方法。在本文中，我们回顾了关于这个主题的文献，并进行了一系列元分析，以确定数字痕迹与特定个体特征（个性、心理健康和智力）之间的关联强度。我们还分析了社交媒体平台类型、所研究的数字痕迹类型和研究质量对潜在调节因素的影响。我们的研究结果表明，社交媒体中的数字痕迹可以用来评估和预测理论上相距甚远的社会心理特征，并且具有相当高的准确性。对调节因素的分析表明，收集特定类型的信息（即用户人口统计信息）和包含不同类型的数字痕迹，可以帮助提高预测的准确性。
