Ontology-Based Information Extraction for Labeling Radical Online Content Using Distant Supervision

Radical, terroristic organizations pose threats to business, government, and society. The ubiquity of the modern Web and its participatory architecture have enabled such groups to become full-blown online propaganda machines. Today, radicalization that eventually leads to acts of terror occurs predominantly on the Web. Radical ideologies can be spread, in many cases unchecked, by malicious actors who take advantage of the frequently lax surveillance apparatus of online social platforms. This paper argues that an overlooked, essential first step to interdicting this threat is the large-scale, structured collection of knowledge regarding these ideologies in open machine-readable formats. Using Collective Action Framing Theory, this study develops a trio of design artifacts: the Terror Beliefs Ontology (TBO) for a general ontology of terroristic ideology, the Frame Discovery System (FDS) to automatically populate this ontology, and the Frame Resonance Detection System (FRDS) to accurately identify online personae or postings that espouse a radical ideology known to TBO. With a comprehensive evaluation, we demonstrate how these three instantiated design artifacts, working in concert, can automatically construct a knowledge representation of heterogeneous terroristic ideologies and accurately detect radical online postings. We offer the first design that can assign Web text to any radical ideology without the use of a hand-labeled training corpus.