Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands

Giuseppe Cascavilla; Gemma Catolino; Fabio Palomba; Andreas S. Andreou; Damian A. Tamburri; Willem Jan Van Den Heuvel

doi:10.1007/978-3-031-18304-1_5

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands

Giuseppe Cascavilla, Gemma Catolino, Fabio Palomba, Andreas S. Andreou, Damian A. Tamburri, Willem Jan Van Den Heuvel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In recent years, job advertisements through the web or social media represent an easy way to spread this information. However, social media are often a dangerous showcase of possibly labor exploitation advertisements. This paper aims to determine the potential indicators of labor exploitation for unskilled jobs offered in the Netherlands. Specifically, we exploited topic modeling to extract and handle information from textual data about job advertisements for analyzing deceptive and characterizing features. Finally, we use these features to investigate whether automated machine learning methods can predict the risk of labor exploitation by looking at salary discrepancies. The results suggest that features need to be carefully monitored, e.g., hours. Finally, our results showed encouraging results, i.e., F1-Score 61%, thus meaning that Data Science methods and Artificial Intelligence approaches can be used to detect labor exploitation—starting from job advertisements—based on the discrepancy of delta salary, possibly representing a revolutionary step.

Original language	English
Title of host publication	Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers
Editors	Johanna Barzen, Frank Leymann, Schahram Dustdar
Publisher	Springer
Pages	79-98
Number of pages	20
ISBN (Print)	9783031183034
DOIs	https://doi.org/10.1007/978-3-031-18304-1_5
Publication status	Published - 2022
Event	16th Symposium and Summer School on Service-Oriented Computing, SummerSOC 2022 - Hersonissos, Greece Duration: 3 Jul 2022 → 9 Jul 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1603 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	16th Symposium and Summer School on Service-Oriented Computing, SummerSOC 2022
Country/Territory	Greece
City	Hersonissos
Period	3/07/22 → 9/07/22

Bibliographical note

Funding Information:
Acknowledgements. We thank Davide Carnevale for the work done during his master thesis. The work is supported by EU Twining DESTINI project, and, the Dutch Ministry of Justice and Safety through the Regional Table Human Trafficking Region East Brabant sponsored the project SENTINEL.

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Funding

Acknowledgements. We thank Davide Carnevale for the work done during his master thesis. The work is supported by EU Twining DESTINI project, and, the Dutch Ministry of Justice and Safety through the Regional Table Human Trafficking Region East Brabant sponsored the project SENTINEL.

Keywords

Artificial Intelligence
Case study
Data science

Access to Document

10.1007/978-3-031-18304-1_5

Cite this

Cascavilla, G., Catolino, G., Palomba, F., Andreou, A. S., Tamburri, D. A., & Van Den Heuvel, W. J. (2022). Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands. In J. Barzen, F. Leymann, & S. Dustdar (Eds.), Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers (pp. 79-98). (Communications in Computer and Information Science; Vol. 1603 CCIS). Springer. https://doi.org/10.1007/978-3-031-18304-1_5

Cascavilla, Giuseppe ; Catolino, Gemma ; Palomba, Fabio et al. / Unsupervised Labor Intelligence Systems : A Detection Approach and Its Evaluation: A Case Study in the Netherlands. Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers. editor / Johanna Barzen ; Frank Leymann ; Schahram Dustdar. Springer, 2022. pp. 79-98 (Communications in Computer and Information Science).

@inproceedings{b03ff6f679054717826cde90690f6057,

title = "Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands",

abstract = "In recent years, job advertisements through the web or social media represent an easy way to spread this information. However, social media are often a dangerous showcase of possibly labor exploitation advertisements. This paper aims to determine the potential indicators of labor exploitation for unskilled jobs offered in the Netherlands. Specifically, we exploited topic modeling to extract and handle information from textual data about job advertisements for analyzing deceptive and characterizing features. Finally, we use these features to investigate whether automated machine learning methods can predict the risk of labor exploitation by looking at salary discrepancies. The results suggest that features need to be carefully monitored, e.g., hours. Finally, our results showed encouraging results, i.e., F1-Score 61\%, thus meaning that Data Science methods and Artificial Intelligence approaches can be used to detect labor exploitation—starting from job advertisements—based on the discrepancy of delta salary, possibly representing a revolutionary step.",

keywords = "Artificial Intelligence, Case study, Data science",

author = "Giuseppe Cascavilla and Gemma Catolino and Fabio Palomba and Andreou, \{Andreas S.\} and Tamburri, \{Damian A.\} and \{Van Den Heuvel\}, \{Willem Jan\}",

note = "Funding Information: Acknowledgements. We thank Davide Carnevale for the work done during his master thesis. The work is supported by EU Twining DESTINI project, and, the Dutch Ministry of Justice and Safety through the Regional Table Human Trafficking Region East Brabant sponsored the project SENTINEL. Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 16th Symposium and Summer School on Service-Oriented Computing, SummerSOC 2022 ; Conference date: 03-07-2022 Through 09-07-2022",

year = "2022",

doi = "10.1007/978-3-031-18304-1\_5",

language = "English",

isbn = "9783031183034",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "79--98",

editor = "Johanna Barzen and Frank Leymann and Schahram Dustdar",

booktitle = "Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers",

address = "Germany",

}

Cascavilla, G, Catolino, G, Palomba, F, Andreou, AS, Tamburri, DA & Van Den Heuvel, WJ 2022, Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands. in J Barzen, F Leymann & S Dustdar (eds), Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers. Communications in Computer and Information Science, vol. 1603 CCIS, Springer, pp. 79-98, 16th Symposium and Summer School on Service-Oriented Computing, SummerSOC 2022, Hersonissos, Greece, 3/07/22. https://doi.org/10.1007/978-3-031-18304-1_5

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands. / Cascavilla, Giuseppe; Catolino, Gemma; Palomba, Fabio et al.
Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers. ed. / Johanna Barzen; Frank Leymann; Schahram Dustdar. Springer, 2022. p. 79-98 (Communications in Computer and Information Science; Vol. 1603 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Unsupervised Labor Intelligence Systems

T2 - 16th Symposium and Summer School on Service-Oriented Computing, SummerSOC 2022

AU - Cascavilla, Giuseppe

AU - Catolino, Gemma

AU - Palomba, Fabio

AU - Andreou, Andreas S.

AU - Tamburri, Damian A.

AU - Van Den Heuvel, Willem Jan

N1 - Funding Information: Acknowledgements. We thank Davide Carnevale for the work done during his master thesis. The work is supported by EU Twining DESTINI project, and, the Dutch Ministry of Justice and Safety through the Regional Table Human Trafficking Region East Brabant sponsored the project SENTINEL. Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2022

Y1 - 2022

N2 - In recent years, job advertisements through the web or social media represent an easy way to spread this information. However, social media are often a dangerous showcase of possibly labor exploitation advertisements. This paper aims to determine the potential indicators of labor exploitation for unskilled jobs offered in the Netherlands. Specifically, we exploited topic modeling to extract and handle information from textual data about job advertisements for analyzing deceptive and characterizing features. Finally, we use these features to investigate whether automated machine learning methods can predict the risk of labor exploitation by looking at salary discrepancies. The results suggest that features need to be carefully monitored, e.g., hours. Finally, our results showed encouraging results, i.e., F1-Score 61%, thus meaning that Data Science methods and Artificial Intelligence approaches can be used to detect labor exploitation—starting from job advertisements—based on the discrepancy of delta salary, possibly representing a revolutionary step.

AB - In recent years, job advertisements through the web or social media represent an easy way to spread this information. However, social media are often a dangerous showcase of possibly labor exploitation advertisements. This paper aims to determine the potential indicators of labor exploitation for unskilled jobs offered in the Netherlands. Specifically, we exploited topic modeling to extract and handle information from textual data about job advertisements for analyzing deceptive and characterizing features. Finally, we use these features to investigate whether automated machine learning methods can predict the risk of labor exploitation by looking at salary discrepancies. The results suggest that features need to be carefully monitored, e.g., hours. Finally, our results showed encouraging results, i.e., F1-Score 61%, thus meaning that Data Science methods and Artificial Intelligence approaches can be used to detect labor exploitation—starting from job advertisements—based on the discrepancy of delta salary, possibly representing a revolutionary step.

KW - Artificial Intelligence

KW - Case study

KW - Data science

UR - http://www.scopus.com/inward/record.url?scp=85140740555&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-18304-1_5

DO - 10.1007/978-3-031-18304-1_5

M3 - Conference contribution

AN - SCOPUS:85140740555

SN - 9783031183034

T3 - Communications in Computer and Information Science

SP - 79

EP - 98

BT - Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers

A2 - Barzen, Johanna

A2 - Leymann, Frank

A2 - Dustdar, Schahram

PB - Springer

Y2 - 3 July 2022 through 9 July 2022

ER -

Cascavilla G, Catolino G, Palomba F, Andreou AS, Tamburri DA , Van Den Heuvel WJ. Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation: A Case Study in the Netherlands. In Barzen J, Leymann F, Dustdar S, editors, Service-Oriented Computing - 16th Symposium and Summer School, SummerSOC 2022, Revised Selected Papers. Springer. 2022. p. 79-98. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-18304-1_5