The Importance of Context in the Automatic Classification of Email as Records of Business Value: a Pilot Study

摘要

Despite the growth of alternative means of electronic messaging,email continues to be a crucial business communicationtool. In many organizations, it is common to find alarge proportion of business-critical data in email form.However, as the volume of business-critical email continuesto grow, conventional approaches for managing paperbasedrecords of business value are increasingly unsuited tothe digital realities. Yet effective approaches to automatethe management of email are essential to ensure organizationalefficiency, accountability and regulatory compliance.Our research aims to develop a model that characterizesinformation managers’ context-specific email triage strategiesfor identifying emails of business value so that it canbe applied to automatically classify email records. We conducteda pilot study of two information managers’ emailtriage practices in two different contexts and develop machine-learning models of lexical and non-lexical featuresthat are involved in the appraisal of business value. An experimentwith a machine learning algorithm trained onabout two hundred emails in two different business contextsindicates that the automation of email triage for identifyingrecords of business value is highly context dependent andthat automated classifiers must be trained to recognize“business value” specifically for that context.