Systematic Review is e-Discovery in Doctor ’ s Clothing

Systematic review [6] and electronic (e-)discovery [9] present similar high-recall information retrieval tasks arising in distinct domains. Both traditionally involve an initial highrecall Boolean search followed by expensive expert review, ultimately yielding a low percentage of relevant documents. Both must account for human error in document review in their processes and evaluation, both face tremendous scalability challenges with ever-larger document collections being searched, and both are increasingly turning to active learning in response [3, 11]. While parallels between these tasks have been briefly noted before [8], research on each still remains largely disjoint today. We argue that the time is now ripe for cross-pollinating research on these tasks.