2020/10/13 by Frances Albert Santos, Santos, Frances, Thiago H. Silva +5
Social Sciences · #Computation and Language (cs.CL) #Digital Marketing and Social Media #FOS: Computer and information sciences #Geographic Information Systems Studies #Human Mobility and Location-Based Analysis #Information Retrieval (cs.IR) #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2010.06444
openalex publication_date 2020/10/13 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
The automatic extraction of urban perception shared by people on\nlocation-based social networks (LBSNs) is an important multidisciplinary\nresearch goal. One of the reasons is because it facilitates the understanding\nof the intrinsic characteristics of urban areas in a scalable way, helping to\nleverage new services. However, content shared on LBSNs is diverse,\nencompassing several topics, such as politics, sports, culture, religion, and\nurban perceptions, making the task of content extraction regarding a particular\ntopic very challenging. Considering free-text messages shared on LBSNs, we\npropose an automatic and generic approach to extract people's perceptions. For\nthat, our approach explores opinions that are spatial-temporal and semantically\nsimilar. We exemplify our approach in the context of urban outdoor areas in\nChicago, New York City and London. Studying those areas, we found evidence that\nLBSN data brings valuable information about urban regions. To analyze and\nvalidate our outcomes, we conducted a temporal analysis to measure the results'\nrobustness over time. We show that our approach can be helpful to better\nunderstand urban areas considering different perspectives. We also conducted a\ncomparative analysis based on a public dataset, which contains volunteers'\nperceptions regarding urban areas expressed in a controlled experiment. We\nobserve that both results yield a very similar level of agreement.\n