Machine learning approach to auto-tagging online content for content marketing efficiency

A comparative analysis between methods and content type

Joni Salminen, Vignesh Yoganathan, Juan Corporan, Bernard Jansen, Soon Gyo Jung

Research output: Contribution to journalArticle

Abstract

As complex data becomes the norm, greater understanding of machine learning (ML)applications is needed for content marketers. Unstructured data, scattered across platforms in multiple forms, impedes performance and user experience. Automated classification offers a solution to this. We compare three state-of-the-art ML techniques for multilabel classification - Random Forest, K-Nearest Neighbor, and Neural Network - to automatically tag and classify online news articles. Neural Network performs the best, yielding an F1 Score of 70% and provides satisfactory cross-platform applicability on the same organisation's YouTube content. The developed model can automatically label 99.6% of the unlabelled website and 96.1% of the unlabelled YouTube content. Thus, we contribute to marketing literature via comparative evaluation of ML models for multilabel content classification, and cross-channel validation for a different type of content. Results suggest that organisations may optimise ML to auto-tag content across various platforms, opening avenues for aggregated analyses of content performance.

Original languageEnglish
Pages (from-to)203-217
Number of pages15
JournalJournal of Business Research
Volume101
DOIs
Publication statusPublished - 1 Aug 2019

Fingerprint

Machine learning
Marketing efficiency
Tagging
Comparative analysis
Tag
Neural networks
Evaluation
K-nearest neighbor
News
Web sites
User experience
Learning model
Marketing
Marketers

Keywords

  • Auto-tagging
  • Content marketing
  • Digital marketing
  • Machine learning
  • Neural network
  • Web content

ASJC Scopus subject areas

  • Marketing

Cite this

Machine learning approach to auto-tagging online content for content marketing efficiency : A comparative analysis between methods and content type. / Salminen, Joni; Yoganathan, Vignesh; Corporan, Juan; Jansen, Bernard; Jung, Soon Gyo.

In: Journal of Business Research, Vol. 101, 01.08.2019, p. 203-217.

Research output: Contribution to journalArticle

@article{986abb1882ee42d1b3d2c02804a3394f,
title = "Machine learning approach to auto-tagging online content for content marketing efficiency: A comparative analysis between methods and content type",
abstract = "As complex data becomes the norm, greater understanding of machine learning (ML)applications is needed for content marketers. Unstructured data, scattered across platforms in multiple forms, impedes performance and user experience. Automated classification offers a solution to this. We compare three state-of-the-art ML techniques for multilabel classification - Random Forest, K-Nearest Neighbor, and Neural Network - to automatically tag and classify online news articles. Neural Network performs the best, yielding an F1 Score of 70{\%} and provides satisfactory cross-platform applicability on the same organisation's YouTube content. The developed model can automatically label 99.6{\%} of the unlabelled website and 96.1{\%} of the unlabelled YouTube content. Thus, we contribute to marketing literature via comparative evaluation of ML models for multilabel content classification, and cross-channel validation for a different type of content. Results suggest that organisations may optimise ML to auto-tag content across various platforms, opening avenues for aggregated analyses of content performance.",
keywords = "Auto-tagging, Content marketing, Digital marketing, Machine learning, Neural network, Web content",
author = "Joni Salminen and Vignesh Yoganathan and Juan Corporan and Bernard Jansen and Jung, {Soon Gyo}",
year = "2019",
month = "8",
day = "1",
doi = "10.1016/j.jbusres.2019.04.018",
language = "English",
volume = "101",
pages = "203--217",
journal = "Journal of Business Research",
issn = "0148-2963",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Machine learning approach to auto-tagging online content for content marketing efficiency

T2 - A comparative analysis between methods and content type

AU - Salminen, Joni

AU - Yoganathan, Vignesh

AU - Corporan, Juan

AU - Jansen, Bernard

AU - Jung, Soon Gyo

PY - 2019/8/1

Y1 - 2019/8/1

N2 - As complex data becomes the norm, greater understanding of machine learning (ML)applications is needed for content marketers. Unstructured data, scattered across platforms in multiple forms, impedes performance and user experience. Automated classification offers a solution to this. We compare three state-of-the-art ML techniques for multilabel classification - Random Forest, K-Nearest Neighbor, and Neural Network - to automatically tag and classify online news articles. Neural Network performs the best, yielding an F1 Score of 70% and provides satisfactory cross-platform applicability on the same organisation's YouTube content. The developed model can automatically label 99.6% of the unlabelled website and 96.1% of the unlabelled YouTube content. Thus, we contribute to marketing literature via comparative evaluation of ML models for multilabel content classification, and cross-channel validation for a different type of content. Results suggest that organisations may optimise ML to auto-tag content across various platforms, opening avenues for aggregated analyses of content performance.

AB - As complex data becomes the norm, greater understanding of machine learning (ML)applications is needed for content marketers. Unstructured data, scattered across platforms in multiple forms, impedes performance and user experience. Automated classification offers a solution to this. We compare three state-of-the-art ML techniques for multilabel classification - Random Forest, K-Nearest Neighbor, and Neural Network - to automatically tag and classify online news articles. Neural Network performs the best, yielding an F1 Score of 70% and provides satisfactory cross-platform applicability on the same organisation's YouTube content. The developed model can automatically label 99.6% of the unlabelled website and 96.1% of the unlabelled YouTube content. Thus, we contribute to marketing literature via comparative evaluation of ML models for multilabel content classification, and cross-channel validation for a different type of content. Results suggest that organisations may optimise ML to auto-tag content across various platforms, opening avenues for aggregated analyses of content performance.

KW - Auto-tagging

KW - Content marketing

KW - Digital marketing

KW - Machine learning

KW - Neural network

KW - Web content

UR - http://www.scopus.com/inward/record.url?scp=85064625684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064625684&partnerID=8YFLogxK

U2 - 10.1016/j.jbusres.2019.04.018

DO - 10.1016/j.jbusres.2019.04.018

M3 - Article

VL - 101

SP - 203

EP - 217

JO - Journal of Business Research

JF - Journal of Business Research

SN - 0148-2963

ER -