“Feeling the Beat”

Abstract

There are few tasks in research more onerous than coding qualitative data. Ironically, the coded data in a qualitative research database themselves represent a great store of knowledge largely untapped by traditional qualitative analysis programs. By “feeling the beat” in data and by using the information that is implicit in coded cases (the metaknowledge), we can develop more intelligent qualitative analysis programs that can offer active assistance with coding, thus reducing the burden to researchers, making coding more efficient, and improving its quality. In this article, the authors examine the coding process, then show how intelligent computational strategies—case-based reasoning, natural-language generation, semantic networks, and production rules—can take advantage of the knowledge implicit in coded information in qualitative databases to help code additional data. This approach dramatically alters the relationship of data to the researcher from passive database to active agent, with important implications for both methodology and theory.