What makes a programming error message good?

Abstract

Programming error messages (PEMs) often prove to be troublesome for novice programmers. Guidelines to improve PEMs often lack theoretical or empirical justification. This research will establish a theoretical foundation for what makes a “good” PEM, based on existing theories that have not yet been applied to PEMs. These findings will be applied to an existing programming environment and result in empirically-validated advice for language implementers.