New Tools for Analyzing Complex Network and Text Data

网络数据和文本数据经常出现在科学和商业的许多不同领域(例如，社交网络、遗传网络、新闻、推文和博客)。如何从网络数据和文本数据中提取信息是统计学和机器学习中非常感兴趣的一个问题。该项目的研究将包括几个部分：(A)收集和清理大规模网络数据集和文本数据集，(B)开发分析网络数据和文本数据的新模型、方法和理论，以及(C)分析PI和合作者收集和清理的大型数据集(数据集是关于统计学家的出版数据)。这项研究将对社会科学、商业，特别是对统计学家的出版模式和趋势的理解产生影响。该项目还为本科生和研究生提供了培训机会。网络数据和文本数据广泛可用，包含回答许多科学问题的有价值的信息。该项目将侧重于网络分析和文本学习，并将在以下专题中作出贡献：(A)开发网络和文本数据模型；(B)开发在计算上可行的网络全球测试、成对比较、动态网络分析和文本学习方法；(C)开发研究统计界研究模式和趋势的新方法。这项研究将在社交网络、基因网络和文本挖掘的应用领域产生新的数据集和新的方法和理论，并将对社会科学、商业和生物学产生影响。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Network data and text data are frequently found in many different areas of science and business (for example, social networks, genetic networks, news, tweets, and blogs). A problem of great interest in statistics and machine learning is how to extract information from network data and text data. The research in this project will have several components: (a) collecting and cleaning large-scale network data sets and text data sets, (b) developing new models, methods, and theory for analyzing network data and text data, and (c) analyzing a large data set, which the PI and collaborators have collected and cleaned (the data set is on the publication data of statisticians). The research will have an impact in social science, business, and especially in understanding the publication patterns and trends of statisticians. The project also provides training opportunities for undergraduate and graduate students. Network data and text data are widely available and contain valuable information for answering many scientific problems. This project will focus on network analysis and text learning and will make contributions in the following topics: (a) development of models for network and text data, (b) development of computationally feasible approaches to network global testing, pairwise comparison, dynamic network analysis, and text learning, and (c) development of new approaches for studying the research patterns and trends of the statistical community. The research will lead to new data sets and new methods and theory in the application areas of social networks, genetic networks, and text mining, and will have an impact in social science, business, and biology.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.