Building expert systems
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The engineering of knowledge-based systems: theory and practice
The engineering of knowledge-based systems: theory and practice
Case-Based Reasoning: Experiences, Lessons and Future Directions
Case-Based Reasoning: Experiences, Lessons and Future Directions
Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Computer Programs for Qualitative Data Analysis: A Software SourceBook
Computer Programs for Qualitative Data Analysis: A Software SourceBook
Using Computers in Qualitative Research
Using Computers in Qualitative Research
Expert Systems
Pattern-Directed Inference Systems
Pattern-Directed Inference Systems
Learning Structural Descriptions From Examples
Learning Structural Descriptions From Examples
Communication and Information Technologies
Social Science Computer Review
Computer-support capabilities for qualitative research in sociology
Automatic Documentation and Mathematical Linguistics
Hi-index | 0.00 |
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.