From spam filtering to information retrieval and back: Seeking conceptual foundations for spam filtering

Email filters removing or tagging messages suspected to be “spam” have become ubiquitous. Presumably, spam filters identify spam messages but a closer look at the filtering process suggests there is a conceptual gap between user-referential definitions of spam (“unsolicited email”) developed in relevant discourse and (often implicit) definitions of spam operationalized by spam filters. In this contribution we outline the gap and explore whether information filtering and information retrieval terminology could be used to conceptualize spam filtering in a systematic, theoretically grounded way, thus helping introduce spam filtering terminology that could be operationalized in a meaningful way.