<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ArticleSet PUBLIC "-//NLM//DTD PubMed 2.7//EN" "https://dtd.nlm.nih.gov/ncbi/pubmed/in/PubMed.dtd">
<ArticleSet>
<Article>
<Journal>
				<PublisherName>انجمن سنجش از دور ایران /  دانشگاه شهید بهشتی</PublisherName>
				<JournalTitle>نشریه سنجش از دور و GIS  ایران</JournalTitle>
				<Issn>2008-5966</Issn>
				<Volume>18</Volume>
				<Issue>2</Issue>
				<PubDate PubStatus="epublish">
					<Year>2026</Year>
					<Month>08</Month>
					<Day>23</Day>
				</PubDate>
			</Journal>
<ArticleTitle>A Hybrid Framework for Enriching Urban Gazetteers by Extracting Geo-Graphic Information from Online Housing Listings</ArticleTitle>
<VernacularTitle>A Hybrid Framework for Enriching Urban Gazetteers by Extracting Geo-Graphic Information from Online Housing Listings</VernacularTitle>
			<FirstPage>37</FirstPage>
			<LastPage>72</LastPage>
			<ELocationID EIdType="pii">106305</ELocationID>
			
<ELocationID EIdType="doi">10.48308/gisj.2025.240702.1280</ELocationID>
			
			<Language>FA</Language>
<AuthorList>
<Author>
					<FirstName>Mahdi</FirstName>
					<LastName>Shakhesi</LastName>
<Affiliation>Dep of Geospatial Information System (GIS), Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, Iran</Affiliation>
<Identifier Source="ORCID">0000-0002-4774-6454</Identifier>

</Author>
<Author>
					<FirstName>Ali Asghar</FirstName>
					<LastName>Alesheikh</LastName>
<Affiliation>Dep of Geospatial Information System (GIS), Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, Iran</Affiliation>
<Identifier Source="ORCID">0000-0001-9537-9401</Identifier>

</Author>
</AuthorList>
				<PublicationType>Journal Article</PublicationType>
			<History>
				<PubDate PubStatus="received">
					<Year>2025</Year>
					<Month>07</Month>
					<Day>16</Day>
				</PubDate>
			</History>
		    <Abstract>Gazetteers are geospatial dictionaries of place names that connect the two concepts of place and space. Providing up-to-date and vernacular geographic information makes user-generated texts valuable for gazetteer enrichment. This study presents a three-tier framework to extract urban geographic information from geotagged housing listings. The first tier is devoted to harvesting main street and neighborhood place names, which the authors usually write without any linguistic clue owing to their well-knownness. Using a random forest model based on a set of spatial measures for each extracted n-gram from the textual content of real estate advertisements enables us to identify the main streets and neighborhoods. We developed a rule-based model to extract all urban place names in the second tier and a linguistic pattern-based model to extract spatial relationships in the third tier. Th​is research focused on the Persian language and Tehran, Mashhad, Isfahan, and Shiraz metropolises from Iran as study regions. The results are encouraging for the first tier, specifically achieving approximately 0.8 and 0.7, respectively, for recall and precision in predicting another metropolis’s main streets and neighborhoods. For the second tier, the precision and recall are near 0.7. However, the framework performed less well in spatial relationship extraction.</Abstract>
			<OtherAbstract Language="FA">Gazetteers are geospatial dictionaries of place names that connect the two concepts of place and space. Providing up-to-date and vernacular geographic information makes user-generated texts valuable for gazetteer enrichment. This study presents a three-tier framework to extract urban geographic information from geotagged housing listings. The first tier is devoted to harvesting main street and neighborhood place names, which the authors usually write without any linguistic clue owing to their well-knownness. Using a random forest model based on a set of spatial measures for each extracted n-gram from the textual content of real estate advertisements enables us to identify the main streets and neighborhoods. We developed a rule-based model to extract all urban place names in the second tier and a linguistic pattern-based model to extract spatial relationships in the third tier. Th​is research focused on the Persian language and Tehran, Mashhad, Isfahan, and Shiraz metropolises from Iran as study regions. The results are encouraging for the first tier, specifically achieving approximately 0.8 and 0.7, respectively, for recall and precision in predicting another metropolis’s main streets and neighborhoods. For the second tier, the precision and recall are near 0.7. However, the framework performed less well in spatial relationship extraction.</OtherAbstract>
		<ObjectList>
			<Object Type="keyword">
			<Param Name="value">gazetteer enrichment</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">spatial relationship extraction</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">geographic information retrieval</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">real estate advertisement</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Random forest</Param>
			</Object>
		</ObjectList>
<ArchiveCopySource DocType="pdf">https://gisj.sbu.ac.ir/article_106305_9008dc13bbfbbbc8b3d3f4e1ded4d0a0.pdf</ArchiveCopySource>
</Article>
</ArticleSet>
