Applying Qualitative Research Methods to Narrative Knowledge Engineering

We propose a methodology for knowledge engineering for narrative intelligence systems, based on techniques used to elicit themes in qualitative methods research. Our methodology uses coding techniques to identify actions in natural language corpora, and uses these actions to create planning operators and procedural knowledge, such as scripts. In an iterative process, coders create a taxonomy of codes relevant to the corpus, and apply those codes to each element of that corpus. These codes can then be combined into operators or other narrative knowledge structures. We also describe the use of this methodology in the context of Dramatis, a narrative intelligence system that required STRIPS operators and scripts in order to calculate human suspense responses to stories. 1998 ACM Subject Classification I.2.4 Knowledge Representation Formalisms and Methods