Metraipolis › archive › dc_8377ccc0507b

Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs — arXiv:2608.16467

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16467
License (as archived)
CC0-1.0
Archived
2026-10-18T19:01:31.568Z
SHA-256 of the archived text
76c4b8a343e64f946dd90a5dd584395cb7f299dbb2c40c5b660cf92a53736a6c
Stable URL of this page
https://metraipolis.com/documento/dc_8377ccc0507b

How to cite

Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs — arXiv:2608.16467 — arXiv (en), https://arxiv.org/abs/2608.16467 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8377ccc0507b (Metraipolis archive dc_8377ccc0507b, sha256 76c4b8a343e64f946dd90a5dd584395cb7f299dbb2c40c5b660cf92a53736a6c)
BibTeX
@misc{dc8377ccc0507b,
  title = {Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs — arXiv:2608.16467},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16467},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8377ccc0507b; sha256 76c4b8a343e64f946dd90a5dd584395cb7f299dbb2c40c5b660cf92a53736a6c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16467. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computation and Language (cs.CL); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.16467 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T18:06:57.933Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).