Applying question answering technology to locating malevolent online content

摘要

We have empirically compared two classes of technologies capable of locating potentially malevolent online content: 1) popular keyword searching, currently widely used by law enforcement and general public, and 2) emerging question answering (QA). The Google search engine exemplified the first approach. To exemplify the second, we further advanced the pattern based probabilistic QA approach and implemented a proof-of-concept prototype that was capable of finding web pages that provide the answers to the given questions, including non-factual ones (e.g. “How to build a pipe bomb?”). The answers to those question typically indicate the presence of malevolent content. Our findings suggest that QA technology can be a good addition to the traditional keyword searching for the task of locating malevolent online content and, possibly, for a more general task of interactive online information exploration.