Geotagging non-spatial concepts

Amgad Madkour, Mohamed Mokbel, Walid G. Aref, Saleh Basalamah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Concept Geo-tagging is the process of assigning a textual identifier that describes a real-world entity to a physical geographic location. A concept can either be a spatial concept where it possesses a spatial presence or be a non-spatial concept where it has no explicit spatial presence. Geo-tagging locations with non-spatial concepts that have no direct relation is a very useful and important operation but is also very challenging. The reason is that, being a non-spatial concept, e.g., crime, makes it hard to geo-tag it. This paper proposes using the semantic information associated with concepts and locations such as the type as a mean for identifying these relations. The co-occurrence of spatial and non-spatial concepts within the same textual resources, e.g., in the web, can be an indicator of a relationship between these spatial and non-spatial concepts. Techniques are presented for learning and modeling relations among spatial and non-spatial concepts from web textual resources. Co-occurring concepts are extracted and modeled as a graph of relations. This graph is used to infer the location types related to a concept. A location type can be a hospital, restaurant, an educational facility and so forth. Due to the immense number of relations that are generated from the extraction process, a semantically-guided query processing algorithm is introduced to prune the graph to the most relevant set of related concepts. For each concept, a set of most relevant types are matched against the location types. Experiments evaluate the proposed algorithm based on its filtering efficiency and the relevance of the discovered relationships. Performance results illustrate how semantically-guided query processing can outperform the baseline in terms of efficiency and relevancy. The proposed approach achieves an average precision of 74% across three different datasets.

Original languageEnglish
Title of host publicationProceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015
PublisherAssociation for Computing Machinery, Inc
Pages31-39
Number of pages9
ISBN (Electronic)9781450339773
DOIs
Publication statusPublished - 3 Nov 2015
Externally publishedYes
Event4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015 - Seattle, United States
Duration: 3 Nov 2015 → …

Other

Other4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015
CountryUnited States
CitySeattle
Period3/11/15 → …

Fingerprint

tagging
crime
resource
Query processing
learning
modeling
Crime
experiment
Semantics
efficiency
hospital
indicator
resources
Experiments

Keywords

  • Geotagging
  • Relatedness

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Computer Networks and Communications
  • Information Systems

Cite this

Madkour, A., Mokbel, M., Aref, W. G., & Basalamah, S. (2015). Geotagging non-spatial concepts. In Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015 (pp. 31-39). Association for Computing Machinery, Inc. https://doi.org/10.1145/2834126.2834138

Geotagging non-spatial concepts. / Madkour, Amgad; Mokbel, Mohamed; Aref, Walid G.; Basalamah, Saleh.

Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015. Association for Computing Machinery, Inc, 2015. p. 31-39.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Madkour, A, Mokbel, M, Aref, WG & Basalamah, S 2015, Geotagging non-spatial concepts. in Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015. Association for Computing Machinery, Inc, pp. 31-39, 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015, Seattle, United States, 3/11/15. https://doi.org/10.1145/2834126.2834138
Madkour A, Mokbel M, Aref WG, Basalamah S. Geotagging non-spatial concepts. In Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015. Association for Computing Machinery, Inc. 2015. p. 31-39 https://doi.org/10.1145/2834126.2834138
Madkour, Amgad ; Mokbel, Mohamed ; Aref, Walid G. ; Basalamah, Saleh. / Geotagging non-spatial concepts. Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015. Association for Computing Machinery, Inc, 2015. pp. 31-39
@inproceedings{c14dddb0bf6e4b939cbf6d7513230b4a,
title = "Geotagging non-spatial concepts",
abstract = "Concept Geo-tagging is the process of assigning a textual identifier that describes a real-world entity to a physical geographic location. A concept can either be a spatial concept where it possesses a spatial presence or be a non-spatial concept where it has no explicit spatial presence. Geo-tagging locations with non-spatial concepts that have no direct relation is a very useful and important operation but is also very challenging. The reason is that, being a non-spatial concept, e.g., crime, makes it hard to geo-tag it. This paper proposes using the semantic information associated with concepts and locations such as the type as a mean for identifying these relations. The co-occurrence of spatial and non-spatial concepts within the same textual resources, e.g., in the web, can be an indicator of a relationship between these spatial and non-spatial concepts. Techniques are presented for learning and modeling relations among spatial and non-spatial concepts from web textual resources. Co-occurring concepts are extracted and modeled as a graph of relations. This graph is used to infer the location types related to a concept. A location type can be a hospital, restaurant, an educational facility and so forth. Due to the immense number of relations that are generated from the extraction process, a semantically-guided query processing algorithm is introduced to prune the graph to the most relevant set of related concepts. For each concept, a set of most relevant types are matched against the location types. Experiments evaluate the proposed algorithm based on its filtering efficiency and the relevance of the discovered relationships. Performance results illustrate how semantically-guided query processing can outperform the baseline in terms of efficiency and relevancy. The proposed approach achieves an average precision of 74{\%} across three different datasets.",
keywords = "Geotagging, Relatedness",
author = "Amgad Madkour and Mohamed Mokbel and Aref, {Walid G.} and Saleh Basalamah",
year = "2015",
month = "11",
day = "3",
doi = "10.1145/2834126.2834138",
language = "English",
pages = "31--39",
booktitle = "Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Geotagging non-spatial concepts

AU - Madkour, Amgad

AU - Mokbel, Mohamed

AU - Aref, Walid G.

AU - Basalamah, Saleh

PY - 2015/11/3

Y1 - 2015/11/3

N2 - Concept Geo-tagging is the process of assigning a textual identifier that describes a real-world entity to a physical geographic location. A concept can either be a spatial concept where it possesses a spatial presence or be a non-spatial concept where it has no explicit spatial presence. Geo-tagging locations with non-spatial concepts that have no direct relation is a very useful and important operation but is also very challenging. The reason is that, being a non-spatial concept, e.g., crime, makes it hard to geo-tag it. This paper proposes using the semantic information associated with concepts and locations such as the type as a mean for identifying these relations. The co-occurrence of spatial and non-spatial concepts within the same textual resources, e.g., in the web, can be an indicator of a relationship between these spatial and non-spatial concepts. Techniques are presented for learning and modeling relations among spatial and non-spatial concepts from web textual resources. Co-occurring concepts are extracted and modeled as a graph of relations. This graph is used to infer the location types related to a concept. A location type can be a hospital, restaurant, an educational facility and so forth. Due to the immense number of relations that are generated from the extraction process, a semantically-guided query processing algorithm is introduced to prune the graph to the most relevant set of related concepts. For each concept, a set of most relevant types are matched against the location types. Experiments evaluate the proposed algorithm based on its filtering efficiency and the relevance of the discovered relationships. Performance results illustrate how semantically-guided query processing can outperform the baseline in terms of efficiency and relevancy. The proposed approach achieves an average precision of 74% across three different datasets.

AB - Concept Geo-tagging is the process of assigning a textual identifier that describes a real-world entity to a physical geographic location. A concept can either be a spatial concept where it possesses a spatial presence or be a non-spatial concept where it has no explicit spatial presence. Geo-tagging locations with non-spatial concepts that have no direct relation is a very useful and important operation but is also very challenging. The reason is that, being a non-spatial concept, e.g., crime, makes it hard to geo-tag it. This paper proposes using the semantic information associated with concepts and locations such as the type as a mean for identifying these relations. The co-occurrence of spatial and non-spatial concepts within the same textual resources, e.g., in the web, can be an indicator of a relationship between these spatial and non-spatial concepts. Techniques are presented for learning and modeling relations among spatial and non-spatial concepts from web textual resources. Co-occurring concepts are extracted and modeled as a graph of relations. This graph is used to infer the location types related to a concept. A location type can be a hospital, restaurant, an educational facility and so forth. Due to the immense number of relations that are generated from the extraction process, a semantically-guided query processing algorithm is introduced to prune the graph to the most relevant set of related concepts. For each concept, a set of most relevant types are matched against the location types. Experiments evaluate the proposed algorithm based on its filtering efficiency and the relevance of the discovered relationships. Performance results illustrate how semantically-guided query processing can outperform the baseline in terms of efficiency and relevancy. The proposed approach achieves an average precision of 74% across three different datasets.

KW - Geotagging

KW - Relatedness

UR - http://www.scopus.com/inward/record.url?scp=84973915416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973915416&partnerID=8YFLogxK

U2 - 10.1145/2834126.2834138

DO - 10.1145/2834126.2834138

M3 - Conference contribution

SP - 31

EP - 39

BT - Proceedings of the 4th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, MobiGIS 2015

PB - Association for Computing Machinery, Inc

ER -