An investigation of crowdsourcing methods in enhancing the machine learning approach for detecting online recruitment fraud

Aug 3, 2026

Upload by Oliver

Misinformation on the web creates a persistent risk for an information-driven society, where online content such as news, jobs, and facts may be unreliable. This research investigates machine learning algorithms for online recruitment fraud (ORF) by testing a job-posting feature model using five supervised methods. It further evaluates crowdsourcing techniques as human signals, comparing hybrid machine-learning plus crowdsourced inputs against automated baselines. Findings show the best algorithm can differ between automated and hybrid setups, and net promoter–style crowdsourced questions deliver strong accuracy for classifying fraudulent versus legitimate jobs.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

Online misinformation and fake content landscape

Online recruitment fraud as a high-impact case

Machine learning approaches for fake content detection

Study motivation and research scope

International Journal of Information Management Data Insights 3 (2023) 100167 Contents lists available at ScienceDirect International Journal of Information Management Data Insights journal [homepage: www.elsevier.com/locate/jjimei](homepage: www.elsevier.com/locate/jjimei) | An investigation of crowdsourcing methods in enhancing the machine learning approach for detecting online recruitment fraud
Krishnadas Nanatha,∗, Liting Olneyb
a Middlesex University Dubai, Springs 3, Villa 3, Dubai, United Arab Emirates b Middlesex University Dubai, Knowledge park, Dubai, United Arab Emirates | | | | | --- | --- | --- | --- | | a r t i c l e i n f o | | a b s t r a c t | | | Keywords: Misinformation Machine learning Crowdsourcing
Fake content
Online recruitment fraud | | Misinformation on the web has become a problem of signiﬁcant impact in an information-driven society. Persistent and large volumes of fake content are being injected, and hence the content (news, articles, jobs, facts) available online is often questionable. This research reviews a range of machine learning algorithms to tackle a speciﬁc case of online recruitment fraud (ORF). A model with content features of job posting is tested with ﬁve supervised machine learning (ML) algorithms. It then investigates various crowdsourcing techniques that could enhance prediction accuracy and add human insights to machine learning automation. Each crowdsourcing method (explored as human signals online) was tested across the same ML algorithms to test its eﬀectiveness in predicting fake job postings. The testing was conducted by comparing the hybrid models of machine learning and crowdsourced inputs. This study revealed that the best ML algorithm was diﬀerent in the automated model compared to the hybrid model. Results also indicated that the net promoter type crowdsourced question resulted in the best accuracy in classifying fraudulent and legitimate jobs. The decision tree and generalized linear model demonstrated the highest accuracy among all the tested models. | | 1. Introduction With the growth of information available on the internet today, the world faces a severe misinformation problem on the web. Fake content on the internet could come in several forms. It could include spam emails, fake news, fake jobs, fake reviews, and rumors. Social media is no longer just a platform to connect with people; it is heavily used for content creation and sharing. With more than 2 billion monthly active users on Facebook1 and 300 million on Twitter2 , content sharing becomes very powerful with the reach it generates on these platforms. The absence of control and fact-checking of online content makes social media platforms a fertile ground for misinformation spread (Zubiaga et al., 2018). Therefore, research on the examination of fake content could make smarter systems for creating a safer web. One category of fake content is the fake jobs that are posted on job portals and professional platforms like LinkedIn.3 In recent years, online recruitment fraud (ORF) in the form of fraudulent job posts online has increasingly become a serious issue. It has resulted in the misuse of personal information and job applicants’ ﬁnancial loss and harming organizations’ credibility (Dutta & Bandyopadhyay;, 2020; Mahbub & ∗ 1 2 3 Corresponding author. [E-mail address:](E-mail address: username.krishna@gmail.com)[ username.krishna@gmail.com](E-mail address: username.krishna@gmail.com) (K. Nanath). [www.facebook.com](www.facebook.com)[ ](www.facebook.com)[www.twitter.com](www.twitter.com)[ ](www.twitter.com)[www.linkedin.com](www.linkedin.com) Pardede, 2018; Vidros et al., 2017). The Federal Bureau of Investigation (2020) issued a public service announcement in January 2020 stating a considerable increase in ORF since early 2019, with an average loss of $3000 per person. Mahab and Pardede (2018) deﬁne online recruitment fraud as “a form of employment scam where a

FAQs

What problem does the study address?

The study targets online recruitment fraud caused by fake job postings, within a broader web misinformation context that can mislead users and harm organizations.

How is machine learning used in the research?

A model built from job-posting content features is evaluated with five supervised machine learning algorithms to classify postings as legitimate or fraudulent.

How do crowdsourcing methods contribute to the results?

Crowdsourcing techniques are tested as human signals and integrated into hybrid models, with performance compared against automated machine-learning baselines using the same classifiers.

Aug 3, 2026

Upload by Oliver