Browsing behavior modeling and browsing interest extraction in the trajectories on web map service platforms. (1st June 2022)

• Record Type: Journal Article
• Authors: Dong, Guangsheng; Li, Rui; Wu, Huayi; Chen, Wenjing; Huang, Wei; Zhang, Hongping
• Is Part Of: Expert systems with applications. Volume 195(2022)
• Publication Date: 2022-06-01
• Subjects: hierarchical Gaussian mixture model -- Multi-granularity -- Browsing interest -- Random forest model -- Trajectories on web map service platform; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.116590
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: The WMSP trajectory of micro process of the browsing behavior is defined. Dimensionality reduction achieves the simplification of the WMSP trajectory. A novel HGMM model is proposed to model spatial structure of the WMSP trajectory. Using RF to filter fake browsing interest based on the spatial attributes. Abstract: Mining the browsing behavior on the web map service platforms (WMSPs) can help to understand the users' access intentions and provide recommendations. Although WMSPs are popular, the research on browsing behavior is in its infancy. The zoom-in indicates interest increasing whereas the zoom-out indicates interest decreasing. We defined the micro process of the users' browsing behavior as the trajectory on the WMSP (WMSP trajectory) reflecting the change of interest. Modeling the WMSP trajectory and extracting its maximum browsing interest (BI) are our objectives. WMSP trajectory has multi-dimensional and multi-granular attributes due to the pyramid model of tiles organization making it challenging to achieve that. We constructed a space–time cube to scan the WMSP trajectory and reduce dimensionality. A new hierarchical Gaussian mixture model (HGMM) was proposed to construct minimum trajectory spanning trees via recursive clustering to model the multi-granular spatial structure and extract BIs. The Random Forest model was used to improve the BIs extraction accuracy. We evaluated the effectiveness of the proposed model using real-world data from Tianditu and proved the HGMM is superior to the GMM. This article will help to make WMSPs intelligent.