A TOPSIS-Inspired Ranking Method Using Constrained Crowd Opinions for Urban Planning

Area of Science:

• Urban Planning
• Data Science
• Crowdsourcing

Background:

• Crowdsourcing is valuable for urban planning knowledge acquisition but faces challenges.
• Traditional crowdsourcing models struggle with complex constraints and diverse opinions in urban planning.
• Existing methods like TOPSIS are limited by conflicting objectives (e.g., benefit vs. cost).

Purpose of the Study:

• To propose a multi-objective approach for aggregating diverse crowd opinions in urban planning.
• To develop a method for ranking crowd workers based on their contributions.
• To overcome limitations of traditional methods when dealing with conflicting urban planning criteria.

Main Methods:

• Developed a multi-objective optimization approach to handle conflicting features in crowd data.
• Implemented a solution to aggregate diverse opinions while satisfying problem-specific constraints.
• Utilized the aggregated solutions to derive an ideal solution for ranking crowd workers.

Main Results:

• The proposed multi-objective approach yields better compromised solutions for urban planning problems.
• The method successfully ranks crowd workers by considering their opinion quality.
• Experimental validation on real-world datasets demonstrates the effectiveness compared to TOPSIS.

Conclusions:

• The novel multi-objective approach enhances knowledge aggregation in urban planning crowdsourcing.
• This method provides a robust framework for dealing with complex, multi-criteria decision-making problems.
• The approach offers improved solutions and reliable crowd worker ranking for urban planning applications.