Electronic evidential data pertaining to a legal case, or a digital forensic investigation can be enormous given the extensive electronic data generation mechanisms of companies and users coupled with cheap storage alternatives. Working with such volumes of data can be tasking, sometimes requiring matured analytical processes and a degree of automation. Once electronic data is collected post eDiscovery hold or post forensic acquisition, it can be framed into datasets for analytical research. This paper focuses on data preprocessing of such evidentiary datasets outlining best practices and potential pitfalls prior to undertaking analytical experiments.
%0 Journal Article
%1 krishnan2021evidence
%A Krishnan, Sundar
%A Shashidhar, Narasimha
%A Varol, Cihan
%A Islam, ABM Rezbaul
%D 2021
%J International Journal of Computational Linguistics (IJCL)
%K Analytics, Digital Electronic Evidence, Forensic Forensics, Information, Language Learning, Legal Machine Natural Preprocessing, Processing Stored eDiscovery,
%N 2
%P 24-34
%T Evidence Data Preprocessing for Forensic and Legal Analytics
%U https://www.cscjournals.org/library/manuscriptinfo.php?mc=IJCL-122
%V 12
%X Electronic evidential data pertaining to a legal case, or a digital forensic investigation can be enormous given the extensive electronic data generation mechanisms of companies and users coupled with cheap storage alternatives. Working with such volumes of data can be tasking, sometimes requiring matured analytical processes and a degree of automation. Once electronic data is collected post eDiscovery hold or post forensic acquisition, it can be framed into datasets for analytical research. This paper focuses on data preprocessing of such evidentiary datasets outlining best practices and potential pitfalls prior to undertaking analytical experiments.
@article{krishnan2021evidence,
abstract = {Electronic evidential data pertaining to a legal case, or a digital forensic investigation can be enormous given the extensive electronic data generation mechanisms of companies and users coupled with cheap storage alternatives. Working with such volumes of data can be tasking, sometimes requiring matured analytical processes and a degree of automation. Once electronic data is collected post eDiscovery hold or post forensic acquisition, it can be framed into datasets for analytical research. This paper focuses on data preprocessing of such evidentiary datasets outlining best practices and potential pitfalls prior to undertaking analytical experiments.},
added-at = {2021-08-26T08:41:05.000+0200},
author = {Krishnan, Sundar and Shashidhar, Narasimha and Varol, Cihan and Islam, ABM Rezbaul},
biburl = {https://www.bibsonomy.org/bibtex/240cde74117cb81a26f4ce6ababacad2f/cscjournals},
interhash = {6d56ba7ce5a299e285491e1bc539bc8b},
intrahash = {40cde74117cb81a26f4ce6ababacad2f},
issn = {2180-1266},
journal = {International Journal of Computational Linguistics (IJCL)},
keywords = {Analytics, Digital Electronic Evidence, Forensic Forensics, Information, Language Learning, Legal Machine Natural Preprocessing, Processing Stored eDiscovery,},
language = {English},
month = {June},
number = 2,
pages = {24-34},
timestamp = {2021-08-26T08:41:05.000+0200},
title = {Evidence Data Preprocessing for Forensic and Legal Analytics},
url = {https://www.cscjournals.org/library/manuscriptinfo.php?mc=IJCL-122},
volume = 12,
year = 2021
}