Christian Schreckenberger, Simon Beckmann, Christian Bartelt
In this systematic literature review an overview of the recent developments in the field of Next Place Prediction is given. Next Place Prediction in this work refers to the prediction of where an individual human will go to next, based on continuous mobility data. It is therefore distinguished from other work in the field of next place prediction that uses, for example check-in data. This review aims to answer the following four questions: (1) Which features are used? (2) Which input data is required? (3) Which technique is used? (4) How is the prediction evaluated?
{"title":"Next Place Prediction: A Systematic Literature Review","authors":"Christian Schreckenberger, Simon Beckmann, Christian Bartelt","doi":"10.1145/3283590.3283596","DOIUrl":"https://doi.org/10.1145/3283590.3283596","url":null,"abstract":"In this systematic literature review an overview of the recent developments in the field of Next Place Prediction is given. Next Place Prediction in this work refers to the prediction of where an individual human will go to next, based on continuous mobility data. It is therefore distinguished from other work in the field of next place prediction that uses, for example check-in data. This review aims to answer the following four questions: (1) Which features are used? (2) Which input data is required? (3) Which technique is used? (4) How is the prediction evaluated?","PeriodicalId":404513,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Prediction of Human Mobility","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125538803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
City connectivity is an important measurement in characterizing human dynamics from regional to international scales. World City Network has been built based on companies' communication. The interactions between spatial and social dimensions of cities have both conceptual and practical significance. To further expand the studies of inter-city network in the big social data context, this research builds a network at the county level using digital footprints from Twitter users. Retrieving geotags from Twitter users, we identify the connection strength of each pair of counties based on the amounts of shared users who leave digital footprints on both counties. Using the shared user amount as the weighted link and each county as the node, we build a county-to-county user flow network. Various network structures have been detected at the state level. In addition, by creating a direct flow chain, we can identify influential counties and its hinterland. This network demonstrates how human mobility operate across various spatial settings and distances. Results of this study can be used in transportation planning, regional planning and metropolitan management.
{"title":"Measuring Inter-city Network Using Digital Footprints from Twitter Users","authors":"Yuqin Jiang, Zhenlong Li, X. Ye","doi":"10.1145/3283590.3283594","DOIUrl":"https://doi.org/10.1145/3283590.3283594","url":null,"abstract":"City connectivity is an important measurement in characterizing human dynamics from regional to international scales. World City Network has been built based on companies' communication. The interactions between spatial and social dimensions of cities have both conceptual and practical significance. To further expand the studies of inter-city network in the big social data context, this research builds a network at the county level using digital footprints from Twitter users. Retrieving geotags from Twitter users, we identify the connection strength of each pair of counties based on the amounts of shared users who leave digital footprints on both counties. Using the shared user amount as the weighted link and each county as the node, we build a county-to-county user flow network. Various network structures have been detected at the state level. In addition, by creating a direct flow chain, we can identify influential counties and its hinterland. This network demonstrates how human mobility operate across various spatial settings and distances. Results of this study can be used in transportation planning, regional planning and metropolitan management.","PeriodicalId":404513,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Prediction of Human Mobility","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132289709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Predicting a person's whereabouts is important in several scenarios. However, it is hard to obtain data that reliably reflects users' mobility patterns. This difficulty has led researchers to use social media data as a proxy to understand and predict human mobility. It has been shown, however, that such data is inherently biased and error-prone, and that such drawbacks may produce sub-par mobility prediction models. In a more narrow context, researchers have used social media data to predict users' check-in patterns. A common approach to alleviate the biases in social media data is to use more than one data source. We here show, however, that the use of data from different social networks does not necessarily increase the predictability of a person next check-in. Our experiments indicate that this result is due to how and where people use different social networks, and that user behavioral characteristics play an important role on the predictability of the next check-in.
{"title":"On the Predictability of a User's Next Check-in Using Data from Different Social Networks","authors":"D. Teixeira, M. Alvim, J. Almeida","doi":"10.1145/3283590.3283592","DOIUrl":"https://doi.org/10.1145/3283590.3283592","url":null,"abstract":"Predicting a person's whereabouts is important in several scenarios. However, it is hard to obtain data that reliably reflects users' mobility patterns. This difficulty has led researchers to use social media data as a proxy to understand and predict human mobility. It has been shown, however, that such data is inherently biased and error-prone, and that such drawbacks may produce sub-par mobility prediction models. In a more narrow context, researchers have used social media data to predict users' check-in patterns. A common approach to alleviate the biases in social media data is to use more than one data source. We here show, however, that the use of data from different social networks does not necessarily increase the predictability of a person next check-in. Our experiments indicate that this result is due to how and where people use different social networks, and that user behavioral characteristics play an important role on the predictability of the next check-in.","PeriodicalId":404513,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Prediction of Human Mobility","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134286776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sungha Ju, Sangyoon Park, Hyoungjoon Lim, S. Yun, J. Heo
Analyzing students' characteristic can provide much information for campus planning, education design and student management. This study built students' sequential trajectories based on student smart card transactions and calculate similarity scores for finding relationship between students' trajectories and academic performance. The data used in this study are student smart card transaction data and attendance information of Yonsei university Songdo campus students. Based on this, the trajectory of each student is created into daily context sequence and connected in semester unit. In order to calculate the similarity of one semester trajectory between two students, Needleman-Wunsch Algorithm, which is mainly used for comparison of the DNA nucleotide sequences of two different species, was applied. The similarity score of trajectory sequences for student pair were calculated for 685 students in spring semester. For finding relation with academic performance, authors divided students into two groups; one group with high similarity score for both students in the pair and the other with pair of students with low similarity score. 2-sample T-test was conducted afterward in to determine whether the GPA of these groups were different form the overall distribution of student GPA. As a result, the mean value of GPA of the students with low similarity scores were statistically significantly lower than the overall mean value of GPA. This means that the trajectory sequence of students with lower GPA is less similar than the other students. The results of this study indicate that trajectory information based on spatial data is related to characteristics such as student academic achievement, and it is possible to analyze characteristics of students through spatial trajectory sequence information.
{"title":"Spatial-Data-Driven Student Characterization: Trajectory Sequence Alignment based on Student Smart Card Transactions","authors":"Sungha Ju, Sangyoon Park, Hyoungjoon Lim, S. Yun, J. Heo","doi":"10.1145/3283590.3283591","DOIUrl":"https://doi.org/10.1145/3283590.3283591","url":null,"abstract":"Analyzing students' characteristic can provide much information for campus planning, education design and student management. This study built students' sequential trajectories based on student smart card transactions and calculate similarity scores for finding relationship between students' trajectories and academic performance. The data used in this study are student smart card transaction data and attendance information of Yonsei university Songdo campus students. Based on this, the trajectory of each student is created into daily context sequence and connected in semester unit. In order to calculate the similarity of one semester trajectory between two students, Needleman-Wunsch Algorithm, which is mainly used for comparison of the DNA nucleotide sequences of two different species, was applied. The similarity score of trajectory sequences for student pair were calculated for 685 students in spring semester. For finding relation with academic performance, authors divided students into two groups; one group with high similarity score for both students in the pair and the other with pair of students with low similarity score. 2-sample T-test was conducted afterward in to determine whether the GPA of these groups were different form the overall distribution of student GPA. As a result, the mean value of GPA of the students with low similarity scores were statistically significantly lower than the overall mean value of GPA. This means that the trajectory sequence of students with lower GPA is less similar than the other students. The results of this study indicate that trajectory information based on spatial data is related to characteristics such as student academic achievement, and it is possible to analyze characteristics of students through spatial trajectory sequence information.","PeriodicalId":404513,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Prediction of Human Mobility","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126661881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Yun, Hieu Minh Nguyen, Sang Yoon Park, Hyoungjoon Lim, J. Heo
Smart city has been a popular research agenda for the past years and have been trying to provide various new services to aid and improve life quality of the public. In this study, the authors utilize floating population analysis to provide 'floating population map', which can better reflect real movement of publics living in Songdo Incheon area. By implementing floating population analysis which contains more information than traditional census population such as hourly based population and weekly based population, the authors used Getis Ord Gi* algorithm and STSS (Space Time Scan Statistics) algorithm to conduct case studies and provided with key scenario which can be implemented into developing smart cities around the world. By using floating population older than 60 years old, new sights for elderly care facilities were derived, also by using floating population data of night time movement, areas which require more security service in the night time were derived. These new insights derived from floating population data could be used as key information for emerging smart cities.
智慧城市在过去几年一直是一个热门的研究议程，并一直试图提供各种新的服务来帮助和提高公众的生活质量。在本研究中，作者利用流动人口分析提供了“流动人口地图”，可以更好地反映松岛仁川地区公众的真实流动情况。通过实施流动人口分析，作者使用Getis Ord Gi*算法和STSS(时空扫描统计)算法进行案例研究，并提供可在全球发展智慧城市中实施的关键场景。流动人口分析比传统的以小时为基础的人口和以周为基础的人口等普查人口包含更多的信息。利用60岁以上的流动人口，推导出养老设施的新景观;利用流动人口夜间流动数据，推导出夜间需要更多安保服务的区域。这些来自流动人口数据的新见解可以作为新兴智慧城市的关键信息。
{"title":"Implementation of Floating Population Analysis for Smart Cities: A case study in Songdo Incheon South Korea","authors":"S. Yun, Hieu Minh Nguyen, Sang Yoon Park, Hyoungjoon Lim, J. Heo","doi":"10.1145/3283590.3283595","DOIUrl":"https://doi.org/10.1145/3283590.3283595","url":null,"abstract":"Smart city has been a popular research agenda for the past years and have been trying to provide various new services to aid and improve life quality of the public. In this study, the authors utilize floating population analysis to provide 'floating population map', which can better reflect real movement of publics living in Songdo Incheon area. By implementing floating population analysis which contains more information than traditional census population such as hourly based population and weekly based population, the authors used Getis Ord Gi* algorithm and STSS (Space Time Scan Statistics) algorithm to conduct case studies and provided with key scenario which can be implemented into developing smart cities around the world. By using floating population older than 60 years old, new sights for elderly care facilities were derived, also by using floating population data of night time movement, areas which require more security service in the night time were derived. These new insights derived from floating population data could be used as key information for emerging smart cities.","PeriodicalId":404513,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Prediction of Human Mobility","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121609420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：