Informing Government Decision-Making with Online Citizen Feedback and Social Media: Pedestrianization of Streets

Abstract

The rise of social media and online platforms allowed citizens to share thoughts and feedback in a digital format, which opens the potential for governments and stakeholders to use data mining to inform design, implementation, and monitoring of public policies and projects. This study presents a case of data mining and analysis of citizen feedback data from multiple platforms: Online survey; Social Media; and Citizen Assembly; to inform policy and decision-making of the Intramuros Administration regarding a proposed pedestrianization of a major street. The study applies a CRISP-DM data mining methodology to pre-process and process feedback data from Facebook, Pol.Is survey platform, and two citizen assemblies, to highlight the key concerns and priorities of constituents regarding the policy topic. Using timeline analysis, principal components analysis, clustering, association rules mining, and topic modeling, the priority concerns of the stakeholders regarding the policy were found to be: security and safety while walking, negative effects of pedestrianization on business, concerns about parking spaces, alternative routes, and accessibility (PWDs and senior citizens). Using the findings as a centerpiece for stakeholder dialogue, the Intramuros Administration and stakeholders discussed in detail, and co-created the proposed next steps to address the concerns raised. The study presents the Intramuros survey case as a replicable model for automation and integration of citizen feedback data in local government policy and decision-making.