ARCHIVED CONTENT
You are viewing ARCHIVED CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active. Content in this archive is NOT UPDATED, and links may not function.This is Part Three of this blog. Please read Part One and Part Two first.
Mitigating Factors to Human Inconsistency
When you consider all of the classifications of documents, both relevant and irrelevant, my consistency rate in the two ENRON reviews jumps to about 99% (01% inconsistent). Compare this with the Grossman Cormack study of the 2009 TREC experiments, where agreement on all non-relevant adjudications, assuming all non-appealed decisions were correct, was 97.4 percent (2.6% inconsistent). My guess is that most well run CAR review projects today are in fact attaining overall high consistency rates. The existing technologies for duplication, similarity, concept and predictive ranking are very good, especially when all used together. When you consider both relevant and irrelevant coding, it should be in the 90s for sure, probably the high nineties. Hopefully, by using todays’ improved software and the latest, fairly simple 8-step methods, we can reduce the relevance inconsistency problem even further. Further scientific research is, however, needed test these hopes and suppositions. My results in the Enron studies could be black swan, but I doubt it. I think my inconsistency is consistent.