基于地理特征嵌入的POI类型表征

IF 0.4 Q4 COMPUTER SCIENCE, INFORMATION SYSTEMS Applied Computing Review Pub Date : 2023-03-27 DOI:10.1145/3555776.3577659
Salatiel Dantas Silva, C. E. Campelo, Maxwell Guimarães De Oliveira
{"title":"基于地理特征嵌入的POI类型表征","authors":"Salatiel Dantas Silva, C. E. Campelo, Maxwell Guimarães De Oliveira","doi":"10.1145/3555776.3577659","DOIUrl":null,"url":null,"abstract":"Representing Points of Interest (POI) types, such as restaurants and shopping malls, is crucial to develop computational mechanisms that may assist in tasks such as urban planning and POI recommendation. The POI co-occurrences in different spatial regions have been used to represent POI types in high-dimensional vectors. However, such representations do not consider the geographic features (e.g. streets, buildings, rivers, parks) in the vicinity of POIs which may contribute to characterize such types. In this context, we propose the Geographic Context to Vector (GeoContext2Vec), an approach that relies on geographic features in the POIs' vicinity to generate POI types representation based on embeddings. We carried out an experiment to evaluate the GeoContext2Vec by using a POI type representation from the state-of-the-art that it does not consider geographic features. The promising results show that the geographic information provided by the GeoContext2Vec outperforms the state-of-the-art and demonstrates the relevance of surrouding geographic features on representing POI type more precisely.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":0.4000,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"POI types characterization based on geographic feature embeddings\",\"authors\":\"Salatiel Dantas Silva, C. E. Campelo, Maxwell Guimarães De Oliveira\",\"doi\":\"10.1145/3555776.3577659\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Representing Points of Interest (POI) types, such as restaurants and shopping malls, is crucial to develop computational mechanisms that may assist in tasks such as urban planning and POI recommendation. The POI co-occurrences in different spatial regions have been used to represent POI types in high-dimensional vectors. However, such representations do not consider the geographic features (e.g. streets, buildings, rivers, parks) in the vicinity of POIs which may contribute to characterize such types. In this context, we propose the Geographic Context to Vector (GeoContext2Vec), an approach that relies on geographic features in the POIs' vicinity to generate POI types representation based on embeddings. We carried out an experiment to evaluate the GeoContext2Vec by using a POI type representation from the state-of-the-art that it does not consider geographic features. The promising results show that the geographic information provided by the GeoContext2Vec outperforms the state-of-the-art and demonstrates the relevance of surrouding geographic features on representing POI type more precisely.\",\"PeriodicalId\":42971,\"journal\":{\"name\":\"Applied Computing Review\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.4000,\"publicationDate\":\"2023-03-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applied Computing Review\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3555776.3577659\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Computing Review","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3555776.3577659","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

表示兴趣点(POI)类型,如餐馆和购物中心,对于开发可能有助于城市规划和POI推荐等任务的计算机制至关重要。利用不同空间区域的POI共现来表示高维向量上的POI类型。然而,这种表述没有考虑到poi附近的地理特征(例如街道、建筑物、河流、公园),这些特征可能有助于描述这类类型。在这种情况下,我们提出了地理上下文到向量(GeoContext2Vec),这是一种依赖于POI附近的地理特征来基于嵌入生成POI类型表示的方法。我们进行了一项实验,通过使用不考虑地理特征的最先进的POI类型表示来评估GeoContext2Vec。结果表明,GeoContext2Vec提供的地理信息优于目前最先进的地理信息,并证明了周围地理特征与更精确地表示POI类型的相关性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
POI types characterization based on geographic feature embeddings
Representing Points of Interest (POI) types, such as restaurants and shopping malls, is crucial to develop computational mechanisms that may assist in tasks such as urban planning and POI recommendation. The POI co-occurrences in different spatial regions have been used to represent POI types in high-dimensional vectors. However, such representations do not consider the geographic features (e.g. streets, buildings, rivers, parks) in the vicinity of POIs which may contribute to characterize such types. In this context, we propose the Geographic Context to Vector (GeoContext2Vec), an approach that relies on geographic features in the POIs' vicinity to generate POI types representation based on embeddings. We carried out an experiment to evaluate the GeoContext2Vec by using a POI type representation from the state-of-the-art that it does not consider geographic features. The promising results show that the geographic information provided by the GeoContext2Vec outperforms the state-of-the-art and demonstrates the relevance of surrouding geographic features on representing POI type more precisely.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Applied Computing Review
Applied Computing Review COMPUTER SCIENCE, INFORMATION SYSTEMS-
自引率
40.00%
发文量
8
期刊最新文献
DIWS-LCR-Rot-hop++: A Domain-Independent Word Selector for Cross-Domain Aspect-Based Sentiment Classification Leveraging Semantic Technologies for Collaborative Inference of Threatening IoT Dependencies Relating Optimal Repairs in Ontology Engineering with Contraction Operations in Belief Change Block-RACS: Towards Reputation-Aware Client Selection and Monetization Mechanism for Federated Learning Elastic Data Binning: Time-Series Sketching for Time-Domain Astrophysics Analysis
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1