The Commonplace
Home Papers Evidence Explore Trends Syntheses Digests References About 🎲 Workforce Futures
← Papers
Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review. How this is built →

Thai university executives reporting stronger digital transformation—notably personnel skills and external networks—and higher AI acceptance also report higher institutional sustainability; a hybrid machine-learning predictor fits the 178-executive sample extremely closely (reported Test R²≈0.95), though the evidence is observational, self-reported, and limited by small-sample external validity.

AI Acceptance and Digital Transformation as Predictive Drivers of University Sustainability Using a Hybrid Machine Learning Model
Seerungrat Sudsomboon, Yuthachai Krokaew, Pawarisa Seangkham, Sutana Boonlua · August 19, 2026 · Research Square
openalex correlational low evidence 5/10 relevance Full text usable extracted full text DOI Source PDF

Structured author observations

Linked only from stored provider relations; the raw author line above is never matched by name.

OpenAlex

Latest observation:

  1. Seerungrat Sudsomboon provider ID
  2. Yuthachai Krokaew provider ID
  3. Pawarisa Seangkham provider ID
  4. Sutana Boonlua provider ID
Survey data from 178 Thai university executives show positive associations between digital technological transformation (especially personnel skills and external networks) and AI acceptance with institutional sustainability, and a hybrid SA-Optuna-Stack machine learning model reportedly predicts sustainability with very high in-sample accuracy (Test R² ≈ 0.95) on the small sample.

Citation observations

Cumulative provider counts captured on specific dates; providers are never combined.

Assessment

Paper Typecorrelational Evidence Strengthlow — Findings are based on a cross-sectional survey of 178 executives and predictive modeling on the same small sample; associations are observational and self-reported without randomized or quasi-experimental identification, objective outcome measures, or external validation, so causal claims and strong generalization are unsupported. Methods Rigormedium — The authors combine conventional regression with a reasonably well-documented hybrid ML pipeline (simulated annealing feature selection, Optuna hyperparameter tuning, stacked ensembling) and report hold-out test metrics and benchmarks; however, sample size is small for the complexity of modeling, measurement appears self-reported, sampling and measurement validity details are limited in the supplied text, and there is no external or out-of-sample validation to rule out overfitting. SampleCross-sectional survey of 178 Thai university executives (reported respondents: Vice Presidents for Administration and Information Technology) providing self-reported measures of six DTT sub-dimensions, six AI acceptance dimensions, and a four-dimension organizational sustainability construct; 29 candidate features used for ML modeling reduced to 12 features, with hold-out test and cross-validation reported. Themesadoption org_design innovation GeneralizabilitySmall sample (n=178) limits statistical power and external validity, Respondents are university executives only (VPs for Admin/IT), not representative of faculty, staff, students, or non-executive institutions, Single-country (Thailand) context with specific policy environment limits applicability to other countries/regions, Outcomes are self-reported survey constructs rather than objective performance or sustainability metrics, Cross-sectional design precludes causal inference and may be subject to common-method bias, ML results lack external validation on independent institutional data and may be overfitted to this sample
Incomplete processing: Summary missing.

Notes