AI summaryⓘ
The authors explain that common methods for understanding customer insights rely heavily on human analysts, which can lead to biased and inconsistent conclusions. They propose a new computational framework called Computational KJ-Ho that uses a specially trained language model to organize and interpret data without human bias. This framework combines ideas from qualitative research and logical reasoning to produce insights and strategies more objectively. They present a theoretical design and initial studies in Japan, emphasizing the importance of tailoring the model for specific domains like marketing. The authors see humans as supervisors rather than main analyzers and plan to test their approach further in the future.
KJ methodGrounded TheoryThematic Analysisanalyst biaslanguage modeldomain specializationmarketing researchPeircean abductioncomputational epistemologyWEIRD problem
Abstract
The qualitative research methodologies that underpin consumer-insight generation - the KJ method, Grounded Theory, and Thematic Analysis - share a structural constraint: the cognitive processing capacity of the human analyst. Replication research further shows that conclusions vary substantially across analysts analyzing identical data (analyst bias). This paper proposes Computational KJ-Ho (the Kawakita Jiro method), a theoretical framework that computationally realizes the KJ method's epistemology - letting structure emerge from the data itself without imposing the analyst's preconceptions - an orientation we term "analyst-bias-free." The framework employs a domain-specialized LLM built through continued pre-training (CPT) on a marketing-research corpus and supervised fine-tuning (SFT) on expert-curated insight pairs, organized as a three-layer architecture: data structuring, insight extraction, and strategy generation. Two preliminary studies in the Japanese marketing context support the necessity of CPT-based domain specialization. The paper makes five contributions: (1) a theoretical integration of the KJ method, Grounded Theory, and Peircean abduction into a single epistemological commitment of data-driven explanation generation; (2) a three-layer architecture leveraging domain-specialized embeddings for cross-interview analysis; (3) two novel evaluation metrics, InsightExtraction-F1 and MarketingQA; (4) explicit engagement with the WEIRD problem, centering a non-Western methodology; and (5) five practice-derived problem formulations from nearly three decades of marketing-research practice, translated into design requirements. The human analyst retains a supervisory role. This is a concept paper presented ahead of empirical validation.