Academic ResearchAugust 20, 2026arXiv (cs.AI, cs.CL)

An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction

A three-part workflow combining a chatbot-administered survey, machine-learning data processing, and LLM-based forecasting to predict weather-sensitive transportation mode choice. Across 454 student observations under five weather conditions, the best vision-augmented LLM configuration reached 71.5% five-class accuracy, showing how multimodal context can strengthen travel demand forecasting.

Authors

Narges Ahmadi, Yubo Jiao, Jônatas Augusto Manzolli, Jiangbo Yu, Luis Miranda-Moreno

Article content

This research proposes an agentic, three-component workflow that combines conversational data collection, data processing, and behavioral forecasting to model travel behavior under different weather conditions. A chatbot-administered survey with visual components gathered transportation mode preferences from students under five weather scenarios, generating 454 observations.

The team analyzed the data with multinomial logit modeling alongside machine-learning techniques, and evaluated nine large language models across a range of configurations.

The best vision-augmented setup achieved 71.5% five-class accuracy, demonstrating the potential of multimodal LLMs for weather-sensitive transportation demand forecasting and, more broadly, for active data collection pipelines in travel and mobility research.

Understanding the acceptance and use of artificial intelligence (AI) as a travel planning tool: UTAUT2 extended model

This study extends the UTAUT2 model with perceived anthropomorphism and perceived intelligence to explain what drives travelers to adopt AI tools for trip planning. Based on 176 survey respondents, performance expectancy, hedonic motivation, perceived anthropomorphism, and perceived intelligence all positively predict behavioral intention, and habit turns out to be central to sustained use.

Academic ResearchJuly 24, 2026

A Sustainability Assessment of Artificial Intelligence Applications in Tourism Management Using an Entropy–TOPSIS Framework

This paper builds an Entropy–TOPSIS framework to rank six AI applications used in tourism management — Generative AI, AI chatbots, digital twin systems, smart destination management, smart governance, and open data tourism platforms — against ten economic, environmental, social, managerial, and ethical criteria. Smart destination management and digital twin systems come out on top, with personalization capability, privacy/ethical risk, and energy efficiency the most discriminating criteria.

For Professors

Submit article for consideration

If you are a professor or researcher and would like to suggest a publicly available article for inclusion in the Research Hub, you can submit it for review and possible inclusion through our dedicated submission form.

Submit research