Paper Abstract
"Local authorities are increasingly using online platforms as a means of involving citizens in urban planning and development. However, they encounter several challenges in the analysis and further processing of citizen-generated data when participation occurs on a large scale. Manual evaluation in particular takes individuals to their limits and hampers value extraction, e.g., for better planning and decision-making. To address these challenges, this paper presents a concept and design guidance based on elicited design requirements of an intelligent system that augments officials in data analytical tasks. Therefore, we focus on a hybrid solution to combine the respective strengths of humans and machines in data processing to mutually overcome their respective weaknesses. Particularly, our solution approach integrates human knowledge in the training process for machine learning via a Human-in-the-Loop strategy and simultaneously facilitates participation data analysis performed by officials. Promising initial evaluation results of the prototype indicate the usefulness of the approach."

The full paper is available through SpringerLink, provided that you have proper access rights.