Identifying human trafficking patterns online

Burbano, Danilo; Hernández-Álvarez, Myriam

doi:10.1109/etcm.2017.8247461

Cited by 12 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One reason is that indicators of sexual exploitation are more discernible and less ambiguous in the online textual context of working offers Di Nicola et al [12]. Burbano et al [4] make a corpus in Spanish language from social media text and build a predictive model in order to identify automatically.…”

Section: Labour Exploitation Identificationmentioning

confidence: 99%

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation

Cascavilla

Catolino

Palomba

et al. 2022

Service-Oriented Computing

View full text Add to dashboard Cite

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, link. Finally, our results showed encouraging results, i.e., F1-Score 61%, thus meaning that Data Science methods and AI approaches can be used to detect labor exploitation-starting from job advertisements -based on the discrepancy of delta salary, possibly representing a revolutionary step.

show abstract

Section: Labour Exploitation Identificationmentioning

confidence: 99%

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation

Cascavilla

Catolino

Palomba

et al. 2022

Service-Oriented Computing

View full text Add to dashboard Cite

show abstract

“…The second approach uses machine learning, data scraping and mining, as well as natural language techniques to discern human trafficking patterns by automatically collecting information from websites dedicated to advertising sex workers' services (Alvari et al, 2016(Alvari et al, , 2017Burbano & Hernandez-Alvarez, 2017;Dubrawski et al, 2015;Hultgren et al, 2018;Portnoff et al, 2017;Szekely et al, 2015;Tong et al, 2017;Whitney et al, 2020). The machine learning algorithm is trained to discern between suspicious and non-suspicious advertisements based on different information.…”

Section: Sex Markets Online Data and Human Traffickingmentioning

confidence: 99%

Identifying human trafficking indicators in the UK online sex market

Giommoni

Ikwu

2021

Trends Organ Crim

View full text Add to dashboard Cite

This study identifies the presence of human trafficking indicators in a UK-based sample of sex workers who advertise their services online. To this end, we developed a crawling and scraping software that enabled the collection of information from 17, 362 advertisements for female sex workers posted on the largest dedicated platform for sex work services in the UK. We then established a set of 10 indicators of human trafficking and a transparent and replicable methodology through which to detect their presence in our sample. Most of the advertisements (58.3%) contained only one indicator, while 3,694 of the advertisements (21.3%) presented 2 indicators of human trafficking. Only 1.7% of the advertisements reported three or more indicators, while there were no advertisements that featured more than four. 3, 255 advertisements (19.0%) did not contain any indicators of human trafficking. Based on this analysis, we propose that this approach constitutes an effective screening process for quickly identifying suspicious cases, which can then be examined by more comprehensive and accurate tools to identify if human trafficking is occurring. We conclude by calling for more empirical research into human trafficking indicators.

show abstract

“…Systems that can assists NGOs and law enforcement exist, of course; for example, in our group, we built the DIG (Domain-specific Insight Graphs) system (Szekely et al 2015) to help law enforcement selectively ferret out ads that are indicative of human trafficking. Other systems include DeepDive and FlagIt, and use a combination of database and Artificial Intelligence technologies Rabbany et al 2018;Alvari et al 2017;Burbano and Hernandez-Alvarez 2017). For example, Rabbany et al (2018) explore methods for active search of connections in order to build cases and combat human trafficking.…”

Section: Online Sex Markets and Artificial Intelligencementioning

confidence: 99%

“…One of the males was clearing moving around the country (and stated explicitly he was on 'tour'), with ads posted from cities as far apart as Glasgow and Birmingham. In conversations with domain experts (especially, human trafficking prosecutors and law enforcement), as well as previously published work in the computational literature, it has been suggested that high degree of movement and the presence of multiple individuals posting from the same account (and frequently changing identity), are textual 'indicators' of human trafficking activity 14 (Burbano and Hernandez-Alvarez 2017;Tong et al 2017). The other male escort changed his name frequently across ads, sometimes going by the name 'Tyler' and at other times, 'Matteo' or even 'Bryan' 15 .…”

Section: Account 129x33xxmentioning

confidence: 99%

Network-theoretic modeling of complex activity using UK online sex advertisements

Kejriwal

2020

Appl Netw Sci

View full text Add to dashboard Cite

Online sex has become a fast-growing business in both developing and developed network, with advertisements of (not necessarily unique) individuals numbering in the hundreds of millions across different Web portals. One such major hub of sex advertisement activity, before it was shut down by US federal agencies, was backpage.com. The backpage.com website was a classifieds-advertising portal that had become the largest marketplace for buying and selling sex by the time that federal law enforcement agencies seized it in April 2018. Since then, investigations have been actively underway. However, the data (which has recently been made available to us for research on UK Backpage) also offers valuable insights into the nature of the online sex business, including complex properties that can be best studied using network science. One of the challenges, however, is a rigorous modeling of the data as a network, since the primary data are web advertisements and metadata (backend database) on accounts that posted that ad. In this article, we conduct an empirical study of an important sample of the online sex marketplace using UK backpage, including presenting a methodology for constructing simple 'activity networks' that define some notion of real-world collaboration or connection between two entities (in our case, at the level of ad-posting accounts) and then studying the properties of these networks. We gather a set of insights into a domain that has not been studied at scale, let alone a national level, but that is continuing to be a growing social problem for many countries.

show abstract

Identifying human trafficking patterns online

Cited by 12 publications

References 21 publications

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation

Unsupervised Labor Intelligence Systems: A Detection Approach and Its Evaluation

Identifying human trafficking indicators in the UK online sex market

Network-theoretic modeling of complex activity using UK online sex advertisements

Contact Info

Product

Resources

About