Intuit Inc.
Method and system for pro-active detection and correction of low quality questions in a question and answer based customer support system

Abstract:

User satisfaction with answers that may be provided through a question and answer based customer support system is predicted by pre-submission analysis of the attributes of the question itself before the answer is generated. Questions being entered into the question and answer based customer support system that are not likely to satisfy either an asking user submitting a question, or subsequent searching users accessing the resulting question and answer pair, are labeled improperly formatted questions, or low quality format questions. The question data representing improperly formatted questions is then either filtered out, avoided completely, or, proactively corrected by providing the user with a set of personalized question format transformation instructions to transform improperly formatted questions into a re-phrased/re-formatted properly formatted questions having a question format predicted to provide a significantly higher probability of user satisfaction with any answer eventually provided.