权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

BIGDATA: Multi-level predictive analytics & motif discovery across massive dynamic spatio-temporal networks in complex socio-technical systems: An organizational genetics appro

大数据：多层次预测分析

基本信息

批准号：
1659998
负责人：
Youngjin Yoo
金额：
$ 61.48万
依托单位：
Case Western Reserve University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2016
资助国家：
美国
起止时间：
2016-07-01 至 2021-01-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1659998&HistoricalAwards=false
关键词：
BIGDATA Multi level predictive analytics

项目摘要

Our lives are becoming increasingly connected with Big Data. Massive amounts of digital trace data are being generated from the activities and events of complex socio-technical systems consisting of human actors and man-made artifacts (which refer to as social objects). Such complexity comes from the massively interconnected and computed nature of the contemporary digital world. These data sets are different from traditional data as they are typically massive, unstructured, granular, heterogeneous, dynamic, and performative. Using Big Data, the researchers are able to understand and predict behaviors of complex socio-technical systems. To support such efforts, the researchers will build a new methodological framework based on an evolutionary ontology that treats variation as real and as the fuel of evolution. Specifically, the researchers analyze data set from Twitter (one of the largest social media sites) and Github (the largest open source community) to test and validate their framework. As the role of Big Data continues to increase in our society, the researchers plan to develop online curricula to help students learn how to access, manage, analyze, and visualize big data sets via a variety of approaches.The researchers are developing a method to predict the emergence of system-level behaviors by analyzing large volumes of digital trace data using evolutionary social ontology to build a multi-level model of complex socio-technical systems. They use analytical techniques developed in evolutionary biology and systems biology: (1) to characterize a stream of digital trace data from a complex socio-technical system with finite genetic elements; (2) to predict the behavior of socio-technical systems based on the pattern of "behavioral gene" interactions; and (3) to explore the impact of mutational input, gene flow, and recombination in "behavioral genes" on the evolution of socio-technical systems. The researchers test their model in GitHub, one of the largest open source communities that includes over 5 million open source software development projects and Twitter, one of the largest social media site, that has over 500 million messages per day. The model generated from this research can be used for other types of massive digital trace data including sensor data from Internet of the Things and mobile data from smartphones.

我们的生活越来越多地与大数据联系在一起。大量的数字痕迹数据是从复杂的社会技术系统的活动和事件中产生的，这些系统由人类行为者和人造物品（称为社会对象）组成。这种复杂性来自当代数字世界的大规模互联和计算性质。这些数据集与传统数据不同，因为它们通常是海量的、非结构化的、粒度的、异构的、动态的和表现性的。利用大数据，研究人员能够理解和预测复杂社会技术系统的行为。为了支持这些努力，研究人员将建立一个新的方法论框架，该框架基于进化本体论，将变异视为真实的和进化的燃料。具体来说，研究人员分析了来自Twitter（最大的社交媒体网站之一）和Github（最大的开源社区）的数据集，以测试和验证他们的框架。随着大数据在我们社会中的作用不断增加，研究人员计划开发在线课程，帮助学生学习如何访问，管理，分析，研究人员正在开发一种方法，通过使用进化社会本体分析大量数字跟踪数据来预测系统级行为的出现，以建立复杂社会行为的多层次模型。技术系统。他们使用进化生物学和系统生物学中发展起来的分析技术：（1）从一个具有有限遗传元素的复杂社会技术系统中描述一系列数字痕迹数据的特征;（2）根据“行为基因”相互作用的模式预测社会技术系统的行为;（3）探讨“行为基因”中的突变输入、基因流动和重组对社会技术系统演化的影响。研究人员在GitHub和Twitter中测试了他们的模型，GitHub是最大的开源社区之一，其中包括超过500万个开源软件开发项目，Twitter是最大的社交媒体网站之一，每天有超过5亿条消息。从这项研究中生成的模型可以用于其他类型的大量数字跟踪数据，包括来自物联网的传感器数据和来自智能手机的移动的数据。