Classifying Latin Inscriptions of the Roman Empire: A Machine-Learning Approach

TY - GEN

T1 - Classifying Latin Inscriptions of the Roman Empire: A Machine-Learning Approach

AU - Kase, Vojtech

AU - Heřmánková, Petra

AU - Sobotková, Adéla

PY - 2021/10/22

Y1 - 2021/10/22

N2 - Large-scale synthetic research in ancient history is often hindered by the incompatibility of taxonomies used by different digital datasets. Using the example of enriching the Latin Inscriptions from the Roman Empire dataset (LIRE), we demonstrate that machine-learning classification models can bridge the gap between two distinct classification systems and make comparative study possible. We report on training, testing and application of a machine learning classification model using inscription categories from the Epigraphic Database Heidelberg (EDH) to label inscriptions from the Epigraphic Database Claus-Slaby (EDCS). The model is trained on a labeled set of records included in both sources (N=46,171). Several different classification algorithms and parametrizations are explored. The final model is based on Extremely Randomized Trees algorithm (ET) and employs 10,055 features, based on several attributes. The final model classifies two thirds of a test dataset with 98% accuracy and 85% of it with 95% accuracy. After model selection and evaluation, we apply the model on inscriptions covered exclusively by EDCS (N=83,482) in an attempt to adopt one consistent system of classification for all records within the LIRE dataset.

AB - Large-scale synthetic research in ancient history is often hindered by the incompatibility of taxonomies used by different digital datasets. Using the example of enriching the Latin Inscriptions from the Roman Empire dataset (LIRE), we demonstrate that machine-learning classification models can bridge the gap between two distinct classification systems and make comparative study possible. We report on training, testing and application of a machine learning classification model using inscription categories from the Epigraphic Database Heidelberg (EDH) to label inscriptions from the Epigraphic Database Claus-Slaby (EDCS). The model is trained on a labeled set of records included in both sources (N=46,171). Several different classification algorithms and parametrizations are explored. The final model is based on Extremely Randomized Trees algorithm (ET) and employs 10,055 features, based on several attributes. The final model classifies two thirds of a test dataset with 98% accuracy and 85% of it with 95% accuracy. After model selection and evaluation, we apply the model on inscriptions covered exclusively by EDCS (N=83,482) in an attempt to adopt one consistent system of classification for all records within the LIRE dataset.

KW - comparative analysis

KW - document classification

KW - epigraphy

KW - latin inscriptions

KW - machine learning

KW - roman empire

KW - type of inscriptions

UR - http://www.scopus.com/inward/record.url?scp=85118831612&partnerID=8YFLogxK

M3 - Article in proceedings

VL - 2989

T3 - CEUR Workshop Proceedings

SP - 123

EP - 135

BT - CHR 2021: Computational Humanities Research 2021

A2 - Ehrmann, M

A2 - Karpsdorp, F

A2 - Wevers, M

A2 - Andrews, T L

A2 - Burghardt, M

A2 - Kestemont, M

A2 - Manjavacas, E

A2 - Piotrowski, M

A2 - van Zhundert, J

T2 - Computational Humanities Research 2021

Y2 - 17 November 2021 through 19 November 2021

ER -