Culturomics is a research project that focuses on comparing word occurrence patterns in different periods of human literature to determine semantic similarity without human intervention. This repository contains the source code from the paper titled "Looking for the Best Historical Window for Assessing Semantic Similarity Using Human Literature" by Jorge Martinez-Gil, Mario Pichler, and Alejandra Lorena Paoletti, presented at EDBT/ICDT Workshops in 2016.
The main goal of Culturomics is to develop computational methods for assessing semantic similarity between words based on their occurrence patterns in historical literature. By analyzing how words co-occur in different time periods, we aim to provide insights into the evolution of language and meaning.
For a detailed understanding of the research and methodologies used in this project, you can refer to the paper available at the following link:
@inproceedings{GilPP16,
author = {Jorge Martinez-Gil and
Mario Pichler and
Alejandra Lorena Paoletti},
editor = {Themis Palpanas and
Kostas Stefanidis},
title = {Looking for the Best Historical Window for Assessing Semantic Similarity
Using Human Literature},
booktitle = {Proceedings of the Workshops of the {EDBT/ICDT} 2016 Joint Conference,
{EDBT/ICDT} Workshops 2016, Bordeaux, France, March 15, 2016},
series = {{CEUR} Workshop Proceedings},
volume = {1558},
publisher = {CEUR-WS.org},
year = {2016},
url = {http://ceur-ws.org/Vol-1558/paper29.pdf}
}