The widespread adoption of Global Positioning Systems (GPS) in transportation has significantly contributed to the understanding of human behavior, enabling the extraction of valuable travel information. However, identifying transportation modes from GPS data remains a complex and under-researched area due to the analytical challenges it presents. While various methods, ranging from rule-based approaches to advanced machine learning algorithms, have been employed to identify transportation modes from GPS data, most have been tested on limited labelled datasets. This study introduces a novel clustering method that combines multi-criteria decision-making, network analysis, and the meta-heuristic algorithm of particle swarm optimization to effectively cluster transportation modes on large dataset. To show the practicality and robustness of this method, we applied it to the MOBIS dataset, which is a large GPS tracking dataset with more than one million trips. By adopting a hybrid approach, the study combines elements from the Analytic Network Process (ANP) super matrix with Particle Swarm Optimization (PSO), using transportation modes as variables and working with fully unlabeled data. The results underscore the model's effectiveness, achieving a high accuracy rate exceeding 92% in transportation mode classification. Moreover, achieving a 10% improvement compared to other studies, this study integrates clustering with the ANP-PSO hybrid method, offering a more promising approach for transportation mode detection, mainly when dealing with large raw GPS data.