Analyzing historians' perspectives using semantic measures

Malic, Vincent Quirante

Permalink

https://hdl.handle.net/2142/89384 Copy

Description

Title

Analyzing historians' perspectives using semantic measures

Author(s)

Malic, Vincent Quirante

Issue Date

2016-03-15

Keyword(s)

• semantic relatedness
• text mining
• knowledge mining
• vector space model
• historiography

Abstract

Historians create structure in our collective understanding of past events. When writing narrative history, they establish connections between significant events, the contexts in which these events occurred, and the people who participated in them. Most of the knowledge created by historians still exists in the form of unstructured texts. This poster presents an exploration of the applicability of the concept of semantic relatedness to historiographical research. Computational methods are applied on texts about the history of the Roman Empire to identify named entities and build word-word relatedness matrices. These matrices are then analyzed to reveal larger thematic structures that characterize a particular historian's view of historical events. This analysis demonstrates the value of semantic relatedness for the unsupervised detection of common themes and unusual outliers in the narrative texts historians have created to store our collective knowledge of the past.

Publisher

iSchools

Series/Report Name or Number

IConference 2016 Proceedings

Type of Resource

text

Language

eng

Permalink

http://hdl.handle.net/2142/89384

DOI

https://doi.org/10.9776/16543

Copyright and License Information

Copyright 2016 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.

Owning Collections