MétaCan
Menu
Back to cohort
Record W4408789181 · doi:10.1016/j.commtr.2025.100172

Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency

2025· article· en· W4408789181 on OpenAlexafffund
Jiangbo Yu, Luis Miranda-Moreno, Matthew Korp

Bibliographic record

VenueCommunications in Transportation Research · 2025
Typearticle
Languageen
FieldEngineering
TopicTransportation and Mobility Innovations
Canadian institutionsMcGill University
FundersEnvironment and Climate Change CanadaMcGill UniversityUniversity of SydneyConcordia UniversityNational Research Foundation SingaporeSingapore-MIT Alliance for Research and Technology CentreMassachusetts Institute of Technology
KeywordsTransparency (behavior)Modular designBusinessComputer scienceComputer security

Abstract

fetched live from OpenAlex

Surveys and interviews—structured, semi-structured, or unstructured—are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. For example, distributed questionnaires lack the ability to provide real-time guidance and request immediate clarifications. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by generative artificial intelligence (AI) technologies. However, considering decisions in transportation investments and policies often carry significant socioeconomic and environmental consequences, surveys and interviews face unique challenges in integrating AI agents. This issue underscors the need for a rigorous, explainable, and resource-efficient approach that enhances participant engagement and ensures privacy. This paper bridges this gap by introducing a modular approach accompanied by a parameterized process for designing and deploying AI agents for surveys and interviews, thereby supporting decision-makings in high-stakes contexts. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting conditional logic and multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) expert consultations about the impact of technologies on future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript postprocessing. The results suggest that the AI agent increases completion rates and response quality. Furthermore, the modular approach demonstrates controllability, flexibility, and robustness while addressing key ethical, privacy, security, and token consumption concerns. We believe this work lays the foundation for next-generation surveys and interviews in transportation research.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.059
metaresearch head score (Gemma)0.092
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.059
Threshold uncertainty score0.311

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0590.092
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.001
Science and technology studies0.0020.005
Scholarly communication0.0050.008
Open science0.0030.015
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0050.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.147
GPT teacher head0.442
Teacher spread0.295 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations10
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueCommunications in Transportation ResearchSame topicTransportation and Mobility InnovationsFrench-language works237,207