Determinants of Organic Agriculture Adoption in Taiwan - A Machine Learning Approach with Methodologic Comparison

Aug 5, 2026

This study examines the determinants of organic agriculture adoption in Taiwan using machine learning methods to connect farmers’ internal motivations with farm characteristics. Data from the 2019 “Social and Cultural Survey of Rural Taiwan” are combined with supplementary 2021 information, and Lasso and Elastic Net regression models are used to identify predictors of willingness to transition. Environmental beliefs show potential causal effects on adoption intentions, while formal education is not significant. Access to information via expert consultation and internet use is crucial, and complex land tenure acts as a barrier. The Elastic Net approach with BIC supports high-dimensional interpretability and the results are compared with prior PCF and multinomial logit work.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages29

Reading Time1 h 13 min

AccessFree to download

Introduction

Theoretical Framework: Internal and External Motivations

Empirical Evidence on Adoption Determinants

Demographic and Human Capital Factors

Structural and Economic Factors

Information Networks and Social Capital

Determinants of Organic Agriculture Adoption in Taiwan: A Machine Learning Approach with Methodological Comparison Tsaiyu Chang * Abstract This study examines the determinants of organic agriculture adoption in Taiwan, employing machine learning techniques to analyze both internal motivations and farm characteristics. Using data from the "Social and Cultural Survey of Rural Taiwan"conducted in 2019 with supplementary data from 2021, we apply Lasso and Elastic Net regression models to identify key predictors of farmers' willingness to transition to organic agriculture. Our analysis suggests that environmental beliefs may have causal effects on adoption intentions, though important methodological limitations should be considered. The empirical analysis reveals that while formal education levels do not significantly influence adoption decisions, access to agricultural information through expert consultation and internet use plays a crucial role. Complex land tenure arrangements emerge as a significant barrier to organic transition, suggesting the importance of institutional factors in adoption decisions. The Elastic Net model with Bayesian Information Criterion offers one approach to handling high-dimensional data while maintaining interpretability, though different methods may be appropriate depending on research objectives and data characteristics. Additionally, this study explicitly compares the results of the machine learning approach with those of Chang (2025), who applied a principal component factoring (PCF) and multinomial logit analysis to the same dataset, highlighting the methodological differences and the policy implications of each. The comparative analysis offers robust evidence regarding the common and distinct drivers of organic agriculture adoption revealed by both analytical frameworks. The findings provide insights that may be relevant for policymakers in Taiwan, though generalization to other contexts would require careful consideration of local agricultural, institutional, and cultural differences. Keywords: organic agriculture adoption, environmental beliefs, farm characteristics, machine learning, economic factors; market development * Faculty of Business Studies, Kyoritsu Women’s University, Tokyo, Japan. mailto: [tchang@kyoritsu-wu.ac.jp](tchang@kyoritsu-wu.ac.jp) ORCID: 0000-0003-1515-1293 1. Introduction Organic farming has emerged as a critical component of sustainable agricultural systems worldwide, offering potential environmental benefits including improved energy efficiency, reduced greenhouse gas emissions, and enhanced biodiversity conservation (Lee et al., 2015) . Despite these recognized benefits, adoption rates vary significantly across regions, with European countries generally demonstrating higher uptake compared to East Asian nations (Willer et al., 2023) . Understanding the factors that influence farmers' decisions to transition to organic farming remains essential for developing effective policies to promote sustainable agricultural practices. 1.1 Theoretical Framework: Internal and External Motivations Research on organic farming adoption has consistently identified two primary categories of motivational factors that influence farmers' transition decisions. Internal motivations stem from farmers' personal values, beliefs, and intrinsic desires, including concerns for personal health, environmental protection, and natural resource stewardship (Mills et al., 2018; De Young, 1985) . These motivations align with self-determination theory, which emphasizes the role of autonomy, competence, and relatedness in driving behavioral change (Deci & Ryan, 1985). External motivations, by contrast, are driven by factors beyond the farmer's immediate control, including market incentives, profitability considerations, consumer recognition, and regulatory frameworks (Genius et al., 2006; Zhang et al., 2018) . This distinction between internal and external motivations provides a u

FAQs

Which factors does the study identify as key predictors of farmers’ organic adoption intentions in Taiwan?

The analysis highlights predictors including the role of environmental beliefs, access to agricultural information through expert consultation and internet use, and the impact of complex land tenure arrangements. Formal education does not show a significant influence on adoption decisions.

How do the authors model adoption determinants using machine learning?

The study uses Lasso and Elastic Net regression models to identify key predictors of willingness to transition to organic agriculture. The Elastic Net model with Bayesian Information Criterion is presented as one way to handle high-dimensional data while maintaining interpretability.

What is the methodological comparison included in the research?

The study compares its machine learning results with Chang (2025), which applied principal component factoring (PCF) and multinomial logit analysis to the same dataset. The comparison clarifies common and distinct drivers of organic adoption and discusses policy implications from each analytical framework.

Aug 5, 2026

Upload by Theodora