{"id":"https://openalex.org/W1966370932","doi":"https://doi.org/10.1145/2184751.2184865","title":"Web community analysis and its application to language specific crawling","display_name":"Web community analysis and its application to language specific crawling","publication_year":2012,"publication_date":"2012-02-20","ids":{"openalex":"https://openalex.org/W1966370932","doi":"https://doi.org/10.1145/2184751.2184865","mag":"1966370932"},"language":"en","primary_location":{"id":"doi:10.1145/2184751.2184865","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184751.2184865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007746447","display_name":"Kulwadee Somboonviwat","orcid":"https://orcid.org/0000-0003-3618-8562"},"institutions":[{"id":"https://openalex.org/I91538806","display_name":"King Mongkut's Institute of Technology Ladkrabang","ror":"https://ror.org/055mf0v62","country_code":"TH","type":"education","lineage":["https://openalex.org/I91538806"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Kulwadee Somboonviwat","raw_affiliation_strings":["King Mongkut's Institute of Technology Ladkrabang (KMITL), Ladkrabang, Bangkok, Thailand","King Mongkut's Institute of Technology Ladkrabang (KMITL), Ladkrabang, Bangkok, Thailand#TAB#"],"affiliations":[{"raw_affiliation_string":"King Mongkut's Institute of Technology Ladkrabang (KMITL), Ladkrabang, Bangkok, Thailand","institution_ids":["https://openalex.org/I91538806"]},{"raw_affiliation_string":"King Mongkut's Institute of Technology Ladkrabang (KMITL), Ladkrabang, Bangkok, Thailand#TAB#","institution_ids":["https://openalex.org/I91538806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007746447"],"corresponding_institution_ids":["https://openalex.org/I91538806"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1358469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9807999730110168,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663730382919312},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7053388357162476},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6597955226898193},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5952099561691284},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5169767141342163},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3398982286453247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663730382919312},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7053388357162476},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6597955226898193},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5952099561691284},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5169767141342163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3398982286453247},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2184751.2184865","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184751.2184865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W97540290","https://openalex.org/W120589439","https://openalex.org/W1489992655","https://openalex.org/W1981202432","https://openalex.org/W1984374364","https://openalex.org/W2020423193","https://openalex.org/W2058113710","https://openalex.org/W2088123540","https://openalex.org/W2128294438","https://openalex.org/W2151626491","https://openalex.org/W4298164899"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2152505903"],"abstract_inverted_index":{"This":[0,32],"paper":[1],"proposes":[2],"a":[3,17,26,68,132],"novel":[4],"metric":[5],"for":[6,140],"web":[7,23,34,45,49,55,69,82,113],"community":[8,18,35,62,92],"analysis,":[9],"called":[10],"language":[11,14,28,74,120,133,143,150],"homogeneity.":[12,75],"The":[13],"homogeneity":[15,111,144],"of":[16,22,44,112,131,149],"measures":[19],"the":[20,30,42,58,90,98,109,147],"ratio":[21],"pages":[24,88],"in":[25,57,97],"specific":[27,121,134,151],"within":[29],"community.":[31],"simple":[33],"analysis":[36,104],"can":[37,115],"provide":[38],"additional":[39],"insights":[40],"on":[41,102],"characteristics":[43],"communities.":[46],"We":[47],"analyze":[48],"communities":[50,83,114],"extracted":[51],"from":[52],"large":[53],"Thai":[54,73,81],"datasets":[56],"following":[59],"aspects:":[60],"(1)":[61],"size":[63],"distribution,":[64],"(2)":[65],"similarity":[66],"with":[67],"directory,":[70],"and":[71,136],"(3)":[72],"Interestingly,":[76],"we":[77,106,126],"found":[78],"that":[79,108],"most":[80],"are":[84],"linguistically":[85],"homogeneous.":[86],"Web":[87],"inside":[89],"same":[91,99],"tend":[93],"to":[94,118,145],"be":[95,116],"written":[96],"language.":[100],"Based":[101],"these":[103],"results,":[105],"argue":[107],"linguistic":[110],"used":[117],"enhance":[119],"crawling.":[122,152],"Towards":[123],"this":[124],"end,":[125],"point":[127],"out":[128],"current":[129],"limitations":[130],"crawler":[135],"suggest":[137],"possible":[138],"ways":[139],"exploiting":[141],"communities'":[142],"improve":[146],"performance":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
