利用社交媒体的位置潜语义特征提取与分析

doi:10.3724/SP.J.1047.2017.01405

地球信息科学学报 ›› 2017, Vol. 19 ›› Issue (11): 1405-1414.doi: 10.3724/SP.J.1047.2017.01405

• 地球信息科学理论与方法 • 下一篇

利用社交媒体的位置潜语义特征提取与分析

陈瑗瑗(), 高勇^*()

北京大学遥感与地理信息系统研究所,北京 100871

收稿日期:2017-07-04 修回日期:2017-09-07 出版日期:2017-11-10 发布日期:2017-11-10
通讯作者: 高勇 E-mail:ygrittechen@pku.edu.cn;gaoyong@pku.edu.cn
作者简介:
作者简介：陈瑗瑗(1994-),女,硕士生,研究方向为空间数据挖掘。E-mail: ygrittechen@pku.edu.cn
基金资助:
国家自然科学基金项目（41625003）

Extracting and Analyzing Latent Semantic Characteristics of Locations Using Social Media Data

CHEN Yuanyuan(), GAO Yong^*()

Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China

Received:2017-07-04 Revised:2017-09-07 Online:2017-11-10 Published:2017-11-10
Contact: GAO Yong E-mail:ygrittechen@pku.edu.cn;gaoyong@pku.edu.cn

摘要/Abstract

摘要：

社交媒体及时、大量、广泛地记录了城市中居民的观点和情感,尤其是具有位置标记的签到文本,将人们所处的空间和城市设施与其相应的认知态度结合起来,成为以人为核心主导的对空间位置特征的直接表达,是场所语义信息的集中体现。以微博签到数据为研究对象,引入自然语言处理领域的潜语义分析的方法,结合空间分析中因子分析、空间自相关分析和聚类分析的手段,提取并分析其中隐含的位置语义特征。本研究主要侧重于对位置之间语义相关程度的度量,首先提取研究区域隐含的概念主题结构,分析不同主题在空间上的分布特征。然后对特定地块进行潜语义空间上的相似性索引,在此基础上,采用先验的百度百科词条描述对位置间语义相似性进行扩展,通过空间自相关的分析,得到不同功能类型的热点区域。

关键词: 位置语义, 社交媒体, 潜语义分析, 场所感知

Abstract:

Social media data are increasingly perceived as an important channel to record people’s perception by virtue of its large volume, availability and timeliness. Especially, some social media data are location-stamped, associating with the space in the city with human cognition. Thus, we can further manifest the sociocultural signature of places in a semantic way. In this paper, geo-tagged text data on Weibo were utilized to explore the hidden semantic characteristics of locations, with focus on semantic similarities among regions. Specifically, Latent Semantic Analysis (LSA) were introduced to transform the unstructured regional and semantic feature in social media into a cognition-friendly and deep-related vector. Then, spatial analysis method, including factor analysis, spatial correlation analysis and clustering analysis were employed to mining the hidden characteristics of locations. In terms of research results, different latent topics and their distribution across the city were uncovered. Similarity index of tested locations were then obtained by measuring their latent semantic features. Baidu-pedia entries were further used as empirical consensus and spatial autocorrelation analysis was employed to investigate urban functional hot-regions. Besides, spatial clusters were acquired by using K-MEANS method in latent semantic space. Its effectiveness was validated by the diversity of POI density among clusters. This study demonstrates how the semantic meaning of a space can be harvested through the analysis of crowd-generated content in social media, which is useful to capture the unique themes that shape a location and support urban planning.

Key words: location semantics, social media, latent semantic analysis, place sensing

陈瑗瑗, 高勇. 利用社交媒体的位置潜语义特征提取与分析[J]. 地球信息科学学报, 2017, 19(11): 1405-1414.DOI:10.3724/SP.J.1047.2017.01405

CHEN Yuanyuan,GAO Yong. Extracting and Analyzing Latent Semantic Characteristics of Locations Using Social Media Data[J]. Journal of Geo-information Science, 2017, 19(11): 1405-1414.DOI:10.3724/SP.J.1047.2017.01405

图/表 6

图1

图2

图3

图4

图5

图6

参考文献 28

[1]	Liu Y, Liu X, Gao S, et al.Social sensing: A new approach to understanding our socioeconomic environments[J]. Annals of the Association of American Geographers, 2015,105(3):512-530. doi: 10.1080/00045608.2015.1018773
[2]	Jiang S, Alves A, Rodrigues F, et al.Mining point-of-interest data from social networks for urban land use classification and disaggregation[J]. Computers Environment & Urban Systems, 2015,53:36-46. doi: 10.1016/j.compenvurbsys.2014.12.001
[3]	Shelton T, Poorthuis A, Graham M, et al.Mapping the data shadows of hurricane sandy: Uncovering the sociospatial dimensions of “big data”[J]. Geoforum, 2014,52(52):167-179. doi: 10.1016/j.geoforum.2014.01.006
[4]	Linna Li, Michael F, Goodchild, Bo Xu.Spatial, temporal, and socioeconomic patterns in the use of twitter and flickr[J]. Cartography and Geographic Information Science, 2013,40(2):61-77. doi: 10.1080/15230406.2013.777139
[5]	Yin Z, Cao L, Han J, et al.Geographical topic discovery and comparison[C]// International Conference on World Wide Web. ACM, 2011:247-256.
[6]	Sizov S.Latent geospatial semantics of social media[J]. Acm Transactions on Intelligent Systems & Technology, 2012,3(4):1-20. doi: 10.1145/2337542.2337549
[7]	Kim K S, Kojima I, Ogawa H.Discovery of local topics by using latent spatio-temporal relationships in geo-social media[J]. International Journal of Geographical Information Science, 2016,30(9):1-24. doi: 10.1080/13658816.2016.1146956
[8]	Lynch K.The Image of the City[M]. Massachusetts: MIT Press, 1960.
[9]	Andrea M, Brandenburg, Matthew S, Carroll. Your place or mine?: The effect of place creation on environmental values and landscape meanings[J]. Society & Natural Resources. An International Journal, 1995,8(5):381-398. doi: 10.1080/08941929509380931
[10]	Williams D R, Stewart S I.Sense of place: an elusive concept that is finding a home in ecosystem management[J]. Journal of Forestry Washington, 1998,96(5):18-23. doi: 10.1007/BF02832964
[11]	Gao Y, Gao S, Li R Q, et al.A semantic geographical knowledge wiki system mashed up with Google Maps[J]. Science China Technological Sciences, 2010,53(1):52-60. doi: 10.1007/s11431-010-3208-0
[12]	李霖,朱海红,王红,等.基于形式本体的基础地理信息语义分析—以陆地水系要素类为例[J].测绘学报,2008,37(2):230-235. doi: 10.3321/j.issn:1001-1595.2008.02.018
	[ Li L, Zhu H H, Wang H, et al.Semantic analyses of the fundamental geographic information based on formal ontology:Exemplifying hydrological category[J]. Acta Geodaetica et Cartographica Sinica, 2008,37(2):230-235. ] doi: 10.3321/j.issn:1001-1595.2008.02.018
[13]	宋佳,诸云强,王卷乐,等.基于GML的时空地理本体模型构建及应用研究[J].地球信息科学学报,2009,11(4):442-451.
	[ Song J, Zhu Y Q, Wang J L, et al.A study on the model of spatio-temporal geo-ontology based on GML[J]. Jounrnal of Geo-Information Science, 2009,11(4):442-451. ]
[14]	Riekert W F.Automated retrieval of information in the internet by using thesauri and gazetteers as knowledge sources. Journal of Universal Computer Science, 2002,8(6):581-590. doi: 10.1145/505241.505246
[15]	Schlieder C, Vogele T, Visser U.Qualitative spatial representation for information retrieval by gazetteers. Proceeding of Cosit' 01 Lncs, 2001:336-351.
[16]	Farazi, Feroz, Vincenzo, et al. A semantic geo-catalogue for a local administration[J]. Artificial Intelligence Review, 2013,40(2):193-212. doi: 10.1007/s10462-012-9353-z
[17]	贾小斌,艾廷华,彭子凤,等.地理信息语义的LOD表达与相似性度量[J].武汉大学学报·信息科学版,2016,41(10):1299-1306. doi: 10.13203/j.whugis20140711
	[ Jia X B, Ai T H, Peng Z F, et al.The LOD expression and proximity measurement of the semantic on geographical information[J]. Geomatics and Information Science of Wuhan University, 2016,41(10):1299-1306. ] doi: 10.13203/j.whugis20140711
[18]	Adams B, Mckenzie G.Inferring thematic places from spatially referenced natural language descriptions[J]. Crowdsourcing Geographic Information, 2013:201-221. doi: 10.1007/978-94-007-4587-2_12
[19]	Lansley G, Longley P A.The geography of twitter topics in London[J]. Computers Environment & Urban Systems, 2016,58:85-96. doi: 10.1016/j.compenvurbsys.2016.04.002
[20]	Andrew J, Arie C, Crooks A T, et al.Crowdsourcing a collective sense of place[J]. Plos One, 2016,11(4):e0152932. doi: 10.1371/journal.pone.0152932 pmid: 27050432
[21]	Landauer T K, Foltz P W, Laham D.Introduction to latent semantic analysis[J]. Discourse Processes, 1998,25(3):259-284. doi: 10.1080/01638539809545028
[22]	Doxas I, Dennis S, Oliver W L.The dimensionality of discourse[J]. Proceedings of the National Academy of Sciences of the United States of America, 2010,107(11):4866. doi: 10.1073/pnas.0908315107
[23]	Zhu M, Ghodsi A.Automatic dimensionality selection from the scree plot via the use of profile likelihood[J]. Computational Statistics & Data Analysis, 2006,51(2):918-930. doi: 10.1016/j.csda.2005.09.010
[24]	易文斌,慎利,齐银凤,等.基于概率潜语义分析模型的高光谱影像层次聚类分析[J].光谱学与光谱分析,2011,31(9):2471-2475.
	[ Yi W B, Shen L, Qi Y F, et al.The hierarchical clustering analysis of hyperspectral images based on probabilistic latent semantic analysis[J]. Spectroscopy & Spectral Analysis, 2011,31(9):2471-2475. ]
[25]	陈黎飞,姜青山,王声瑞.基于层次划分的最佳聚类数确定方法[J].软件学报,2008,19(1):62-72. doi: 10.3724/SP.J.1001.2008.00062
	[ Chen L F, Jiang Q S, Wang S R, et al.A hierarchical method for determining the number of clusters[J]. Journal of Software, 2008,19(1):62-72. ] doi: 10.3724/SP.J.1001.2008.00062
[26]	Wei C,Yang C,Lin C.A latent semantic indexing-based approach to multilingual document clustering[J]. Decision Support Systems,2008,45(3):606-620.
	[ Chen L, Jiang Q, Wang S.A hierarchical method for determining the number of clusters[J]. Journal of Software, 2008,45(3):606-620. ]
[27]	Evangelopoulos N, Zhang X, Prybutok V R.Latent semantic analysis: Five methodological recommendations[J]. European Journal of Information Systems, 2012,21(1):70-86. doi: 10.1057/ejis.2010.61
[28]	康朝贵. 基于个体时空轨迹数据的居民移动模式和城市空间结构分析方法[D].北京:北京大学,2015.
	[ Kang C G.Sensing urban space from human activity and its spatio-temporal characteristics[D]. Beijing: Peking University, 2015. ]

利用社交媒体的位置潜语义特征提取与分析

Extracting and Analyzing Latent Semantic Characteristics of Locations Using Social Media Data

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 28

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	杨腾飞, 解吉波, 李振宇, 李国庆. 微博中蕴含台风灾害损失信息识别和分类方法[J]. 地球信息科学学报, 2018, 20(7): 906-917.
[2]	梁春阳, 林广发, 张明锋, 汪玮杨, 张文富, 林金煌, 邓超. 社交媒体数据对反映台风灾害时空分布的有效性研究[J]. 地球信息科学学报, 2018, 20(6): 807-816.