User identification can help us build more comprehensive user information. It has been attracting much attention from academia. Most of the existing works are profile-based user identification and relationship-based user identification. Due to user privacy settings and social network restrictions on user data crawl, user data may be missing or incomplete in real social networks. User data include profiles, user-generated contents (UGCs), and relationships. The features extracted in previous research may be sparse. In order to reduce the impact of the above problems on user identification, we propose a multiple user information user identification framework (MUIUI). Firstly, we develop multiprocess crawlers to obtain the user data from two popular social networks, Twitter and Facebook. Secondly, we use named entity recognition and entity linking to obtain and integrate locations and organizations from profiles and UGCs. We also extract URLs from profiles and UGCs. We apply the locations jointly with the relationships and develop several algorithms to measure the similarity of the display name, all locations, all organizations, location in profile, all URLs, following organizations, and user ID, respectively. Afterward, we propose a fusion classifier machine learning-based user identification method. The results show that the F1 score of MUIUI reaches 86.46% on the dataset. It proves that MUIUI can reduce the impact of user data that are missing or incomplete.

The recreation opportunity spectrum (ROS) has been widely recognized as an effective tool for the inventory and planning of outdoor recreational resources. However, its applications have been primarily focused on forest-dominated settings with few studies being conducted on all land types at a regional scale. The creation of a ROS is based on physical, social, and managerial settings, with the physical setting being measured by three criteria: remoteness, size, and evidence of humans. One challenge to extending the ROS to all land types on a large scale is the difficulty of quantifying the evidence of humans and social settings. Thus, this study, for the first time, developed an innovative approach that used night lights as a proxy for evidence of humans and points of interest (POI) for social settings to generate an automatic ROS for Hunan Province using Geographic Information System (GIS) spatial analysis. The whole province was classified as primitive (2.51%), semi-primitive non-motorized (21.33%), semi-primitive motorized (38.60%), semi-developed natural (30.99%), developed natural (5.61%), and highly developed (0.96%), which was further divided into three subclasses: large-natural (0.63%), small natural (0.27%), and facilities (0.06%). In order to implement the management and utilization of natural recreational resources in Hunan Province at the county (city, district) level, the province’s 122 counties (cities, districts) were categorized into five levels based on the ROS factor dominance calculated at the county and provincial levels. These five levels include key natural recreational counties (cities, districts), general natural recreational counties (cities, districts), rural counties (cities, districts), general metropolitan counties (cities, districts), and key metropolitan counties (cities, districts), with the corresponding numbers being 8, 21, 50, 24, and 19, respectively.