Smart literature review: a practical topic modelling approach to exploratory literature review

Bidragets oversatte titel: Smart Literatur Review: En praktisk topic model tilgang til eksplorative literature review

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

30 Downloads (Pure)

Resumé

Manual exploratory literature reviews should be a thing of the past, as technology and development of machine learning methods have matured. The learning curve for using machine learning methods is rapidly declining, enabling new possibilities for all researchers. A framework is presented on how to use topic modelling on a large collection of papers for an exploratory literature review and how that can be used for a full literature review. The aim of the paper is to enable the use of topic modelling for researchers by presenting a step-by-step framework on a case and sharing a code template. The framework consists of three steps; pre-processing, topic modelling, and post-processing, where the topic model Latent Dirichlet Allocation is used. The framework enables huge amounts of papers to be reviewed in a transparent, reliable, faster, and reproducible way.
OriginalsprogEngelsk
Artikelnummer93
TidsskriftJournal of Big Data
Vol/bind6
Udgave nummer1
Sider (fra-til)1-18
Antal sider18
ISSN2196-1115
DOI
StatusUdgivet - 19 okt. 2019

Emneord

  • Supply Chain Managment
  • Latent Dirichlet Allocation
  • Topic modelling
  • Automatic literature review

Citer dette

@article{ed8dfd302a924025a4773df53e7a5c2b,
title = "Smart literature review: a practical topic modelling approach to exploratory literature review",
abstract = "Manual exploratory literature reviews should be a thing of the past, as technology and development of machine learning methods have matured. The learning curve for using machine learning methods is rapidly declining, enabling new possibilities for all researchers. A framework is presented on how to use topic modelling on a large collection of papers for an exploratory literature review and how that can be used for a full literature review. The aim of the paper is to enable the use of topic modelling for researchers by presenting a step-by-step framework on a case and sharing a code template. The framework consists of three steps; pre-processing, topic modelling, and post-processing, where the topic model Latent Dirichlet Allocation is used. The framework enables huge amounts of papers to be reviewed in a transparent, reliable, faster, and reproducible way.",
keywords = "Supply Chain Managment, Latent Dirichlet Allocation, Topic modelling, Automatic literature review",
author = "Asmussen, {Claus Boye} and Charles M{\o}ller",
year = "2019",
month = "10",
day = "19",
doi = "10.1186/s40537-019-0255-7",
language = "English",
volume = "6",
pages = "1--18",
journal = "Journal of Big Data",
issn = "2196-1115",
publisher = "Springer Nature",
number = "1",

}

Smart literature review : a practical topic modelling approach to exploratory literature review. / Asmussen, Claus Boye; Møller, Charles.

I: Journal of Big Data, Bind 6, Nr. 1, 93, 19.10.2019, s. 1-18.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Smart literature review

T2 - a practical topic modelling approach to exploratory literature review

AU - Asmussen, Claus Boye

AU - Møller, Charles

PY - 2019/10/19

Y1 - 2019/10/19

N2 - Manual exploratory literature reviews should be a thing of the past, as technology and development of machine learning methods have matured. The learning curve for using machine learning methods is rapidly declining, enabling new possibilities for all researchers. A framework is presented on how to use topic modelling on a large collection of papers for an exploratory literature review and how that can be used for a full literature review. The aim of the paper is to enable the use of topic modelling for researchers by presenting a step-by-step framework on a case and sharing a code template. The framework consists of three steps; pre-processing, topic modelling, and post-processing, where the topic model Latent Dirichlet Allocation is used. The framework enables huge amounts of papers to be reviewed in a transparent, reliable, faster, and reproducible way.

AB - Manual exploratory literature reviews should be a thing of the past, as technology and development of machine learning methods have matured. The learning curve for using machine learning methods is rapidly declining, enabling new possibilities for all researchers. A framework is presented on how to use topic modelling on a large collection of papers for an exploratory literature review and how that can be used for a full literature review. The aim of the paper is to enable the use of topic modelling for researchers by presenting a step-by-step framework on a case and sharing a code template. The framework consists of three steps; pre-processing, topic modelling, and post-processing, where the topic model Latent Dirichlet Allocation is used. The framework enables huge amounts of papers to be reviewed in a transparent, reliable, faster, and reproducible way.

KW - Supply Chain Managment

KW - Latent Dirichlet Allocation

KW - Topic modelling

KW - Automatic literature review

UR - http://www.scopus.com/inward/record.url?scp=85073674481&partnerID=8YFLogxK

U2 - 10.1186/s40537-019-0255-7

DO - 10.1186/s40537-019-0255-7

M3 - Journal article

AN - SCOPUS:85073674481

VL - 6

SP - 1

EP - 18

JO - Journal of Big Data

JF - Journal of Big Data

SN - 2196-1115

IS - 1

M1 - 93

ER -