Learning to Classify Email into "Speech Acts".
William W. Cohen, Vitor Rocha de Carvalho, Tom M. Mitchell · 2004
It is often useful to classify email according to the intent of the sender (e.g., "propose a meeting", "deliver information"). We present experimental results in learning to classify email in this fashion, where each class corresponds to a verb-noun pair taken from a predefined ontology describing typical “email speech acts”. We demonstrate that, although this categorization problem is quite different from “topical ” text classification, certain categories of messages can nonetheless be detected with high precision (above 80%) and reasonable recall (above 50%) using existing text-classification learning methods. This result suggests that useful tasktracking tools could be constructed based on automatic classification into this taxonomy. 1