In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.

Increasing electric vehicle (EV) shares and fuel economy pose challenges to a fuel tax-based transportation funding scheme. This paper evaluates such fuel tax revenue impacts using Virginia as a case study. First, a bivariate count model is developed using vehicle registration data in 132 counties from 2012 to 2016. Model results indicate strong correlation between presence of battery electric vehicles (BEVs) and plug-in hybrid electric vehicles (PHEVs) on a county basis. Counties with higher percent of males are associated with higher BEV (but not PHEV) counts. In contrast, higher average commute time is predicted to increase the number of PHEVs in each county, but not BEVs. Greater population density, population over 65, population with graduate degrees, and household size are found to increase PHEV and BEV counts, whereas more households with children is associated with fewer EVs. The analysis forecasts 0.6–10% statewide EV adoption by 2025, with an adoption rate of 2.4% in the most likely scenario. Nine scenarios, combining different predictions of EV adoption and fuel economy improvement, project 2025 statewide fuel tax revenue to decrease by 5–19%, relative to 2016 receipts. Furthermore, model results suggest that, on average, a light-duty vehicle in a rural area will pay 28% more in fuel taxes than its urban counterpart by 2025. The framework proposed here provides a reference for other regions to conduct similar analysis using public agency data in the vehicle electrification era.

Public perception and attitudes towards public affairs in the USA since the 1960s become a societal issue of growing importance in the field of planning. Good land-use planning should deliver a bright future vision in a way that unites and inspires groups to implement it. The introduction of public perception into planning helps to understand the process of how the public develop their awareness, value judgments, behavior and attitudes. In this research, we built the framework of public perception in land-use planning based on the affect, behavior, cognition (ABC) theory of consumer behavior. We gathered empirical data for Jiangsu province in China. We used structural equation modeling, a commonly used statistical analysis method for examining the structural relationship between multiple variables. We found that the public perception towards public affairs contributed to forming a multiple iterative interaction effect, which evolves a process from primary cognition to knowledge extraction, internalized absorption, emotional judgement and finally externalization into a certain attitudes and behaviors. On the cognitive level, our research result showed that public expectation and perceived quality have opposite effects on perceived difference and the public expectation is more influential. If the planning vision provides a clear and convincing picture of the future, and the information of planning is easy to understand, the public’s cognition and emotion can be well integrated. The core element of the emotional level is perceived value. The public is more concerned about a new planning project if it can add the value to the land, protect community environment, and improve the condition of low-income and minority populations. On the behavior level, public continuous behavior intentions could enhance perceived value, subjective norms and perceived availability. The research could further account for the root of public attitudes and behavior. This is crucial to China's land-use policy, and may well provide important lessons for other developing countries.