Uncovering and Managing the Impact of Methodological Choices for the Computational Construction of Socio-Technical Networks from Texts
Abstract
This thesis is motivated by the need for scalable, robust and reliable methods and technologies that support the construction of network data from natural language text data, and the usage of the extracted data for answering substantive and graph-theoretical questions about sociotechnical networks. The findings and technology resulting from this thesis improve the applicability of language technologies for generating network data based on text data; thereby advancing the intersection of network analysis and text analysis. This thesis contributes to the actionable meaning of network data by providing methods that leverage theories from the social sciences to construct and analyze network data, and to combine text data and network data for analysis.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2012
- Accession Number
- AD1153027
Entities
People
- Jana Diesner
Organizations
- Carnegie Mellon University