This guide promotes the use of sentiment analysis as a technique for analyzing the presence of human trafficking in escort ads pulled from the open web. Sentiment analysis of web data is an approach to discern the text writer’s affinity or negativity as expressed through her use of language and vocabulary. The prevalence of human trafficking has also democratized its presence in digital mediums and it is clear that the Internet has become a home for the proliferation of trafficking and for conducting trafficking as a business. Many websites have been widely used as a digital marketplace for predators and pimps to traffic victims through solicitation of services, especially in the area of sex-trafficking. Traditional techniques have not focused on sentiment as a textual cue of human trafficking and instead have focused on other visual cues (e.g., presence of tattoos in associated images), or textual cues (specific styles of ad-writing; keywords, etc.). This guide applies two widely cited sentiment analysis models: the Netflix and Stanford model, and also its own binary and categorical (multi- class) sentiment model using escort review data extracted from the open web. The individual model performances and exploratory analysis motivated researchers to construct two ensemble sentiment models that correctly serve as a feature proxy to identify human trafficking 53% of the time when evaluated against a set of 38,563 ads provided by the DARPA MEMEX project.

Ensemble Sentiment Analysis to Identify Human Trafficking in Web Data - Graph Techniques for Adversarial Activity Analytics, 2018 DOWNLOAD

post

page

attachment

revision

nav_menu_item

custom_css

customize_changeset

oembed_cache

user_request

wp_block

wp_template

wp_template_part

wp_global_styles

wp_navigation

wp_font_family

wp_font_face

acf-taxonomy

acf-post-type

acf-field-group

acf-field

ai1ec_event

exactmetrics_note

Review of the Nestlé Palm Oil Upstream Supply Chain Management Program in Malaysia and Indonesia
Guidance

In recent years, labour practices in the palm oil sector in Southeast Asia have drawn significant attention from both media and civil society actors. In June 2018, Nestlé began a partnership with Verité on a multiyear program to improve ...Read More

Measuring modern slavery: Moving beyond prevalence
Guidance

Modern Slavery Evidence Unit (MSEU) Research Briefing 11: on an article by Professor Todd Landman, May 2020 Lessons learned in the measurement of human rights can, and are, being applied to the measurement of modern slavery. The anti-slavery sect...Read More

TAGS: Global
State of remedy 2021: Understanding OECD Guidelines complaints through the lens of remedy
Guidance

The year 2021 marked another discouraging year in terms of remedy for complaints by communities and civil society under the OECD Guidelines for Multinational Enterprises (Guidelines). Only 2 of the 22 cases concluded in 2021 by National Contact Poin...Read More

Quality Standards for Reporting Lines for Child Sexual Exploitation in Travel and Tourism
GuidancePublications

These quality standards are a practical tool for the staff managing these reporting websites or wishing to create one. They cover several aspects, in particular: The checking of the background and the references of employeesThe processing of repo...Read More