Plastic bag ban -- causal policy analysis using NLP and citizen data
Jakarta implemented a plastic bag ban in 2020 -- prohibiting single-use plastic bag distribution by retailers. Policy makers needed empirical evidence of the ban's effectiveness to justify regulatory enforcement costs and inform decisions about extending similar restrictions to other waste categories. No quantitative impact evaluation had been conducted using the city's own citizen complaint data platforms.
Causal identification is non-trivial in this setting. The plastic bag ban coincided with COVID-19 lockdown measures that dramatically reduced retail footfall and waste generation -- a massive confounding event that would inflate any naive pre-post comparison. Controlling for pandemic-period mobility restrictions, economic activity reduction, and seasonal waste patterns simultaneously requires explicit causal inference methodology, not simple before-after descriptive statistics.
Applied difference-in-differences (DiD) causal inference framework using NLP-classified citizen waste complaints from JAKI (Jakarta's official smart city complaint platform) and Qlue (a civic reporting platform). 100,000+ complaint records classified by waste type using text classification -- distinguishing plastic-specific complaints from general waste, sanitation, and other urban service complaints. Plastic-specific complaints serve as the treatment group; non-plastic waste complaints serve as the control group within the same platform and time period.
Controlled for: COVID-19 mobility reduction (using Google Community Mobility Reports as a proxy), seasonal waste volume patterns, and platform reporting activity levels (to distinguish real-world waste changes from changes in complaint behavior).
Identified statistically significant reduction in plastic-specific complaints post-ban-implementation, controlling for pandemic confounders. Pre-registered hypotheses and transparent methodology presented at ICISS 2021.
Provided empirical causal evidence for the plastic bag ban's effectiveness -- the first quantitative impact evaluation using Jakarta's own citizen complaint infrastructure. Methodology is directly replicable for evaluating future environmental regulations (food container bans, extended producer responsibility policies) at city scale. Presented to 500+ international attendees at IEEE-sponsored ICISS 2021, establishing this as a template for evidence-based urban environmental policy evaluation in emerging market smart cities.