DEVELOPING AND VALIDATING A TEXT MINING DICTIONARY FOR MEASURING DYNAMIC CAPABILITIES IN THE INSURANCE INDUSTRY: A STUDY IN THE VIETNAMESE MARKET
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no3E.481Keywords:
Dynamic Capabilities, text mining, InsurTech dictionary, insurance industry, methodological validation.Abstract
The study presents the process of constructing and validating a specialized Text Mining Dictionary designed to measure Dynamic Capabilities (DC) in Vietnam's insurance industry. Teece's (2007) microfoundations theoretical framework, encompassing three dimensions - Sensing, Seizing, and Transforming - is applied to guide the construction and classification of keywords. The four-step validation process comprises: construction of a preliminary dictionary (seed dictionary) derived from InsurTech terminology; expert validation through the Fleiss' kappa coefficient; statistical validation of convergent validity against hard financial proxy variables; and controlling for the cheap talk phenomenon by cross-referencing text mining scores with Technology CAPEX data. The dictionary is illustrated through the annual reports of publicly listed insurance companies. The results yield a high-reliability measurement instrument that addresses the inherent limitations of the time lag approach in measuring DC. The insurance industry-specific bilingual Vietnamese–English keyword dictionary is designed for release as an open-source resource to facilitate reuse by the academic community.
References
[1] D. J. Teece, "Explicating dynamic capabilities: The nature and microfoundations of (sustainable) enterprise performance," Strateg. Manage. J., vol. 28, no. 13, pp. 1319–1350, Dec. 2007, doi: https://doi.org/10.1002/smj.640
[2] O. Schilke and C. E. Helfat, "Unlocking dynamic capabilities: Pathways for empirical research," J. Manage. Sci. Rep., vol. 3, no. 2, 2025, doi: https://doi.org/10.1177/27550311251318724
[3] J. A. Bingler, M. Kraus, M. Leippold, and N. Webersinke, "How cheap talk in climate disclosures relates to climate initiatives, corporate emissions, and reputation risk," J. Banking Finance, vol. 164, p. 107191, Jul. 2024, doi: https://doi.org/10.1016/j.jbankfin.2024.107191
[4] D. J. Teece, G. Pisano, and A. Shuen, "Dynamic capabilities and strategic management," Strateg. Manage. J., vol. 18, no. 7, pp. 509–533, Aug. 1997, doi: https://doi.org/10.1002/(SICI)1097-0266(199708)18:7<509::AID-SMJ882>3.0.CO;2-Z
[5] M. Musaigwa and F. Netswera, "Transforming insurance: The impact of digital technologies on operations and processes," Int. J. Appl. Res. Bus. Manage., vol. 6, no. 1, pp. 1–18, 2025, doi: https://doi.org/10.51137/wrp.ijarbm.2025.mmti.45818
[6] T. Loughran and B. McDonald, "When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks," J. Finance, vol. 66, no. 1, pp. 35–65, Feb. 2011, doi: https://doi.org/10.1111/j.1540-6261.2010.01625.x
[7] A. Goldfarb and C. Tucker, "Digital economics," J. Econ. Lit., vol. 57, no. 1, pp. 3–43, Mar. 2019, doi: https://doi.org/10.1257/jel.20171452
[8] C. Marquis, M. W. Toffel, and Y. Zhou, "Scrutiny, norms, and selective disclosure: A global study of greenwashing," Organ. Sci., vol. 27, no. 2, pp. 483–504, Apr. 2016, doi: https://doi.org/10.1287/orsc.2015.1039
[9] T. P. Lyon and J. W. Maxwell, "Greenwash: Corporate environmental disclosure under threat of audit," J. Econ. Manage. Strategy, vol. 20, no. 1, pp. 3–41, Mar. 2011, doi: https://doi.org/10.1111/j.1530-9134.2010.00282.x
[10] M. Lang and L. Stice-Lawrence, "Textual analysis and international financial reporting: Large sample evidence," J. Account. Econ., vol. 60, no. 2–3, pp. 110–135, Nov.–Dec. 2015, doi: https://doi.org/10.1016/j.jacceco.2015.09.002
[11] J. Huang, D. D. Wang, and Y. Wang, "Textual attributes of corporate sustainability reports and ESG ratings," Sustainability, vol. 16, no. 21, p. 9270, Oct. 2024, doi: https://doi.org/10.3390/su16219270
[12] G. Melloni, A. Caglio, and P. Perego, "Saying more with less? Disclosure conciseness, completeness and balance in Integrated Reports," J. Account. Public Policy, vol. 36, no. 3, pp. 220–238, May–Jun. 2017, doi: https://doi.org/10.1016/j.jaccpubpol.2017.03.001
[13] R. A. Cazier, J. L. McMullin, and J. S. Treu, "Are lengthy and boilerplate risk factor disclosures inadequate? An examination of judicial and regulatory assessments of risk factor language," Account. Rev., vol. 96, no. 4, pp. 131–155, Jul. 2021, doi: https://doi.org/10.2308/TAR-2018-0657
[14] X. Zhu, J. Li, and Y. Wang, "Are risk disclosures in financial reports informative? A text mining-based perspective," Humanit. Soc. Sci. Commun., vol. 11, art. no. 1653, Dec. 2024, doi: https://doi.org/10.1057/s41599-024-04169-w
[15] Y. Lin, R. Shen, J. Q. Wang, and Y. Yu, "Global evolution of environmental and social disclosure in annual reports," J. Account. Res., vol. 62, no. 5, pp. 1941–1988, 2024, doi: https://doi.org/10.1111/1475-679X.12575
[16] B. P. Miller, "The effects of reporting complexity on small and large investor trading," Account. Rev., vol. 85, no. 6, pp. 2107–2143, Nov. 2010, doi: https://doi.org/10.2308/accr.00000001
[17] I. Laksmana, W. Tietz, and Y.-W. Yang, "Compensation discussion and analysis (CD&A): Readability and management obfuscation," J. Account. Public Policy, vol. 31, no. 2, pp. 185–203, Mar.–Apr. 2012, doi: https://doi.org/10.1016/j.jaccpubpol.2011.08.003
[18] M. Nadeem, "Board gender diversity and managerial obfuscation: Evidence from the readability of narrative disclosure in 10-K reports," J. Bus. Ethics, vol. 179, no. 1, pp. 153–177, Jun. 2022, doi: https://doi.org/10.1007/s10551-021-04830-3
[19] D. M. Merkl-Davies, N. M. Brennan, and S. J. McLeay, "Impression management and retrospective sense-making in corporate narratives: A social psychology perspective," Account. Audit. Account. J., vol. 24, no. 3, pp. 315–344, 2011, doi: https://doi.org/10.1108/09513571111124036
[20] T. P. Wisniewski and L. S. Yekini, "Stock market returns and the content of annual report narratives," Account. Forum, vol. 39, no. 4, pp. 281–294, Dec. 2015, doi: https://doi.org/10.1016/j.accfor.2015.09.001
[21] L. T. H. Tran et al., "Annual report narrative disclosures, information asymmetry and future firm performance: Evidence from Vietnam," Int. J. Emerg. Mark., vol. 18, no. 2, pp. 351–375, 2023, doi: https://doi.org/10.1108/IJOEM-08-2020-0925
[22] Q. Deng, M. J. Hine, S. Ji, and S. Sur, "Inside the black box of dictionary building for text analytics: A design science approach," J. Int. Technol. Inf. Manage., vol. 27, no. 3, pp. 119–159, 2019, doi: https://doi.org/10.58729/1941-6679.1376
[23] J. L. Fleiss, "Measuring nominal scale agreement among many raters," Psychol. Bull., vol. 76, no. 5, pp. 378–382, 1971, doi: https://doi.org/10.1037/h0031619
[24] E. Brynjolfsson, D. Rock, and C. Syverson, "The productivity J-curve: How intangibles complement general purpose technologies," Nat. Bureau Econ. Res., Cambridge, MA, USA, Working Paper 25148, Oct. 2018, doi: https://doi.org/10.3386/w25148
[25] D. Q. Nguyen and A. T. Nguyen, "PhoBERT: Pre-trained language models for Vietnamese", in Findings of the Assoc. Comput. Linguist.: EMNLP 2020, Nov. 2020, pp. 1037–1042, doi: https://doi.org/10.18653/v1/2020.findings-emnlp.92
