Date of Graduation
7-2026
Document Type
Thesis
Degree Name
Master of Science in Computer Science (MS)
Degree Level
Graduate
Department
Electrical Engineering and Computer Science
Advisor/Mentor
Nelson, Alexander
Committee Member
Andrews, David
Second Committee Member
Gauch, Susan
Keywords
Semantic Analysis; Space Syntax Analysis; Watershed Segmentation
Abstract
Archaeological datasets frequently combine architectural plans, geographic information, textual descriptions, and imagery, making quantitative analysis across these heterogeneous data sources challenging. This thesis presents a reproducible computational pipeline for integrating spatial and semantic archaeological data into a unified analytical framework. The proposed methodology constructs an architectural graph through automated segmentation, associates artifacts with graph regions through georeferencing, and derives semantic representations of artwork using large language models and vector embeddings. These integrated datasets enable statistical evaluation of relationships between artifact content and architectural graph metrics. The framework was demonstrated using the archaeological site of Pompeii. Statistical analysis identified a significant relationship between depictions of Jupiter and degree centrality while the remaining tested hypotheses were not supported, illustrating the framework’s ability to quantitatively evaluate archaeological hypotheses without consistently producing positive results. The primary contribution of this work is a generalizable computational methodology for integrating heterogeneous archaeological datasets and enabling reproducible spatial-semantic analysis within digital archaeology.
Citation
Greenway, L. M. (2026). Enabling Digital Humanities Research Through Topographical Graph Creation And Analysis. Graduate Theses and Dissertations Retrieved from https://scholarworks.uark.edu/etd/6418
