The covert nature of sex trafficking provides a barrier to generating large-scale, data-driven insights to inform law enforcement, policy and social work. We leverage massive deep web data (collected from leading commercial sex websites) with a novel machine learning framework to study how and where sex worker recruitment occurs. We provide a geographical network view of commercial sex supply chains, highlighting deceptive recruitment-to-sales pathways that signal high trafficking risk.

Firms use social impact claims to attract workers, but the credibility of these claims is understudied. We suggest that when social impact is presented as corporate purpose, firm capacity is a key source of credibility. Using an online job board, we use topic modeling to confirm that (i) firms present social impact as purpose, (ii) purpose claims attract job seekers, and (iii) the latter effect is moderated by firm size. We experimentally confirm that perceptions of capacity drive our results.