Many methods have been used to generate gridded population maps by downscaling demographic data. As one of these methods, the accuracy of the dasymetric model depends heavily on the covariates. Point-of-interest (POI) data, as important covariates, have been widely used for population estimation. However, POIs are often used indiscriminately in existing studies. A few studies further used selected categories of POIs identified based only on the nonspatial quantitative relationship between the POIs and population. In this paper, the spatial association between the POIs and population distribution was considered to identify the POIs with a strong spatial correlation with the population distribution, i.e., population-sensitive POIs. The ability of population-sensitive POIs to improve the fine-grained population mapping accuracy was explored by comparing the results of random forest dasymetric models driven by population-sensitive POIs, all POIs, and no POIs, along with the same sets of multisource remote sensing and social sensing data. The results showed that the model driven by population-sensitive POI had the highest accuracy. Population-sensitive POIs were also more effective in improving the population mapping accuracy than were POIs selected based only on their quantitative relationship with the population. The model built using population-sensitive POIs also performed better than the two popular gridded population datasets WorldPop and LandScan. The model we proposed in this study can be used to generate accurate spatial population distribution information and contributes to achieving more reliable analyses of population-related social problems.Dasymetric mapping, on the other hand, was used to generate the 1-km LandScan [5] and the 100-m WorldPop [18] annual population datasets.Dasymetric mapping is a well-known cartographic approach for generating high-resolution population maps [22][23][24]. The idea of dasymetric mapping is to generate a weighting layer using different kinds of covariates. This layer will then be used to redistribute the demographic data. Dasymetric mapping has been demonstrated to be more effective in generating more accurate population estimates than other approaches [25,26]. In the context of dasymetric mapping, the accuracy of the population estimates depends greatly on the covariates used [27]. Remote sensing products and geospatial big data are the most commonly used covariates in dasymetric mapping [1,3,18,[28][29][30][31][32][33][34][35]. Remotely sensed population-related products, such as land use/land cover (LULC) data and nighttime light (NTL) data, could show the actual surface conditions that reflect the physical factors that affect the population distribution. However, these data often lack semantic information. Semantic information can be used to describe the relationship between geographic attributes and geographic features, such as different human activities occurring at accurate geographic locations. With the development of location-aware devices and the emergence and p...