{"id":"https://openalex.org/W4404612057","doi":"https://doi.org/10.1145/3678717.3691215","title":"CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl","display_name":"CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4404612057","doi":"https://doi.org/10.1145/3678717.3691215"},"language":"en","primary_location":{"id":"doi:10.1145/3678717.3691215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678717.3691215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3678717.3691215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075611724","display_name":"Ilya Ilyankou","orcid":"https://orcid.org/0009-0008-7082-7122"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ilya Ilyankou","raw_affiliation_strings":["UCL SpaceTimeLab, London, UK"],"raw_orcid":"https://orcid.org/0009-0008-7082-7122","affiliations":[{"raw_affiliation_string":"UCL SpaceTimeLab, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071454135","display_name":"Meihui Wang","orcid":"https://orcid.org/0000-0001-8420-2141"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meihui Wang","raw_affiliation_strings":["UCL SpaceTimeLab, London, UK"],"raw_orcid":"https://orcid.org/0000-0001-8420-2141","affiliations":[{"raw_affiliation_string":"UCL SpaceTimeLab, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024272400","display_name":"Stefano Cavazzi","orcid":"https://orcid.org/0000-0003-3575-0365"},"institutions":[{"id":"https://openalex.org/I1342692935","display_name":"Ordnance Survey","ror":"https://ror.org/02xqyv944","country_code":"GB","type":"government","lineage":["https://openalex.org/I1342692935"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefano Cavazzi","raw_affiliation_strings":["Ordnance Survey, Southampton, UK"],"raw_orcid":"https://orcid.org/0000-0003-3575-0365","affiliations":[{"raw_affiliation_string":"Ordnance Survey, Southampton, UK","institution_ids":["https://openalex.org/I1342692935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056082244","display_name":"James Haworth","orcid":"https://orcid.org/0000-0001-9506-4266"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Haworth","raw_affiliation_strings":["UCL SpaceTimeLab, London, UK"],"raw_orcid":"https://orcid.org/0000-0001-9506-4266","affiliations":[{"raw_affiliation_string":"UCL SpaceTimeLab, London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66752328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"693","last_page":"696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9735000133514404,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.8211911916732788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6928086280822754},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5320618748664856},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3659210205078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3469586968421936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3303939998149872},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.16636383533477783},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13960745930671692}],"concepts":[{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.8211911916732788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928086280822754},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5320618748664856},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3659210205078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3469586968421936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3303939998149872},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.16636383533477783},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13960745930671692},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678717.3691215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678717.3691215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3678717.3691215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678717.3691215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2170716095","https://openalex.org/W3164301942","https://openalex.org/W4308521115","https://openalex.org/W4385990940","https://openalex.org/W4399511044"],"related_works":["https://openalex.org/W4367313141","https://openalex.org/W2004086023","https://openalex.org/W2733999579","https://openalex.org/W2110217573","https://openalex.org/W4283374591","https://openalex.org/W2910751785","https://openalex.org/W4390100400","https://openalex.org/W4366547507","https://openalex.org/W4362512700","https://openalex.org/W2074396925"],"abstract_inverted_index":{"The":[0,20,105],"Common":[1],"Crawl":[2],"(CC)":[3],"corpus":[4],"is":[5,22,149],"the":[6,84,99,116],"largest":[7],"open":[8],"web":[9],"crawl":[10],"dataset":[11,21,87,106],"containing":[12],"9.5+":[13],"petabytes":[14],"of":[15,60,91,142],"data":[16,97],"captured":[17],"since":[18],"2008.":[19],"instrumental":[23],"in":[24,81,140],"training":[25],"large":[26],"language":[27],"models,":[28,134],"and":[29,39,83,94],"as":[30,57,124,126],"such":[31],"it":[32],"has":[33,51],"been":[34,52],"studied":[35],"for":[36,41,127,136],"(un)desirable":[37],"content,":[38],"distilled":[40],"smaller,":[42],"domain-specific":[43],"datasets.":[44],"However,":[45],"to":[46,54,72,110],"our":[47],"knowledge,":[48],"no":[49],"research":[50],"dedicated":[53],"using":[55],"CC":[56,103],"a":[58],"source":[59],"annotated":[61,74],"geospatial":[62],"data.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"introduce":[68],"an":[69],"efficient":[70],"pipeline":[71],"extract":[73],"user-generated":[75],"tracks":[76],"from":[77,98],"GPX":[78],"files":[79],"found":[80],"CC,":[82],"resulting":[85],"multimodal":[86],"with":[88],"1,416":[89],"pairings":[90],"human-written":[92],"descriptions":[93],"MultiLineString":[95],"vector":[96],"6":[100],"most":[101],"recent":[102],"releases.":[104],"can":[107],"be":[108],"used":[109],"study":[111],"people's":[112],"outdoor":[113,122],"activity":[114],"patterns,":[115],"way":[117],"people":[118],"talk":[119],"about":[120],"their":[121],"experiences,":[123],"well":[125],"developing":[128],"trajectory":[129],"generation":[130],"or":[131,135],"track":[132],"annotation":[133],"various":[137],"other":[138],"problems":[139],"place":[141],"synthetically":[143],"generated":[144],"routes.":[145],"Our":[146],"reproducible":[147],"code":[148],"available":[150],"on":[151],"GitHub:":[152],"https://github.com/ilyankou/cc-gpx.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}