From fragmented survey evidence to transferable behavioral models: a framework for electric vehicle adoption

Understanding heterogeneous household responses is essential for modeling electric-vehicle (EV) adoption, yet survey evidence remains fragmented across studies, constructs, samples, and specifications. This study develops an evidence-integration workflow that organizes dispersed findings through a demographic-psychological-purchase-intention (D→P→PI) architecture. Using EV adoption as an application, we establish a common micro-level platform from the China Household Finance Survey, initialize demographic-to-psychological mappings through literature-informed construct alignment assisted by large language models, and refine parameters by reverse calibration against nine EV-adoption studies. Reverse calibration increases the mean cross-study reproduction score from 74 to 86 on a 0-100 scale; conditional leave-one-study-out structural reproduction yields a mean score of 82. The workflow integrates heterogeneous survey findings into a transparent, auditable behavioral layer for travel-behavior and transport-modeling research.

Authors

Institutions

Publication Details

Journal
Transportation Letters
Published
2026-11-17
DOI
https://doi.org/10.1080/19427867.2026.2764452
Primary Topic
Electric Vehicles and Infrastructure
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

From fragmented survey evidence to transferable behavioral models: a framework for electric vehicle adoption

Shanyuan Zhang, Songmin Yu
Transportation Letters
Electric Vehicles and Infrastructure
article

From fragmented survey evidence to transferable behavioral models: a framework for electric vehicle adoption

Shanyuan Zhang, Songmin Yu
article en

Abstract

Understanding heterogeneous household responses is essential for modeling electric-vehicle (EV) adoption, yet survey evidence remains fragmented across studies, constructs, samples, and specifications. This study develops an evidence-integration workflow that organizes dispersed findings through a demographic-psychological-purchase-intention (D→P→PI) architecture. Using EV adoption as an application, we establish a common micro-level platform from the China Household Finance Survey, initialize demographic-to-psychological mappings through literature-informed construct alignment assisted by large language models, and refine parameters by reverse calibration against nine EV-adoption studies. Reverse calibration increases the mean cross-study reproduction score from 74 to 86 on a 0-100 scale; conditional leave-one-study-out structural reproduction yields a mean score of 82. The workflow integrates heterogeneous survey findings into a transparent, auditable behavioral layer for travel-behavior and transport-modeling research.

Transportation Letters
Tianjin University (CN), Cosmote (Greece) (GR), Fraunhofer Institute for Systems and Innovation Research (DE)
Electric Vehicles and Infrastructure
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon