This (incorrect assumptions leading to frustration) is definitely the most troubling thing to me about automagic solutions. I'm currently working on a project that incorporates this idea of sorting email into contexts (http://solnovus.com, not much info up as of yet), so we've been thinking a lot about this problem specifically.
We are working in user-defined contexts from day one (not all users fit into the 5-context model), but I think incorrect classification is the most important issue to address to minimize user frustration. We are approaching it by treating topic and context membership fuzzily and using graph visualization to aid in traversal of inexact queries.
I couldn't agree with you more: there are serious problems with binary membership and "automatic" filtering.
We are working in user-defined contexts from day one (not all users fit into the 5-context model), but I think incorrect classification is the most important issue to address to minimize user frustration. We are approaching it by treating topic and context membership fuzzily and using graph visualization to aid in traversal of inexact queries.
I couldn't agree with you more: there are serious problems with binary membership and "automatic" filtering.