Currently, the adoption of electric vehicles (EV) draws much attention, as the environmental issue of reducing carbon emission is increasing worldwide. However, different countries face different challenges during this transition, particularly developing countries. This research aims to create a framework for the transition to EV in Indonesia through Agent-Based Modeling (ABM). The framework is used as the conceptual design for ABM to investigate the effect of agents’ decision-making processes at the microlevel into the number of adopted EV at the macrolevel. The cluster analysis is equipped to determine the agents’ characteristics based on the categories of the innovation adopters. There are 11 significant variables and four respondents’ clusters: innovators, early majority, late majority, and the uncategorized one. Moreover, Twitter data analytics are utilized to investigate the information engagement coefficient based on the agents’ location. The agents’ characteristics which emerged from this analysis framework will be used as the fundamental for investigating the effect of agents’ specific characteristics and their interaction through ABM for further research. It is expected that this framework will enable the discovery of which incentive scheme or critical technical features effectively increase the uptake of EV according to the agents’ specific characteristics.
COVIDSenti: A Large-Scale Benchmark Twitter Data Set for COVID-19 Sentiment Analysis