{"id":"https://openalex.org/W2160970157","doi":"https://doi.org/10.1109/cmpsac.2003.1245399","title":"Intelligent Web topics search using early detection and data analysis","display_name":"Intelligent Web topics search using early detection and data analysis","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2160970157","doi":"https://doi.org/10.1109/cmpsac.2003.1245399","mag":"2160970157"},"language":"en","primary_location":{"id":"doi:10.1109/cmpsac.2003.1245399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cmpsac.2003.1245399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003","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/A5060927749","display_name":"Ching-Cheng Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I127339247","display_name":"California State University System","ror":"https://ror.org/020qm1538","country_code":"US","type":"education","lineage":["https://openalex.org/I127339247"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ching-Cheng Lee","raw_affiliation_strings":["Mathematics and Computer Science, California State University, Hayward, Hayward, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science, California State University, Hayward, Hayward, CA, USA","institution_ids":["https://openalex.org/I127339247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100935401","display_name":"Yixin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I127339247","display_name":"California State University System","ror":"https://ror.org/020qm1538","country_code":"US","type":"education","lineage":["https://openalex.org/I127339247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Yang","raw_affiliation_strings":["Mathematics and Computer Science, California State University, Hayward, Hayward, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science, California State University, Hayward, Hayward, CA, USA","institution_ids":["https://openalex.org/I127339247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060927749"],"corresponding_institution_ids":["https://openalex.org/I127339247"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14837173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.98580002784729,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9839000105857849,"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":0.8001763224601746},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7843308448791504},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7758304476737976},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6898412704467773},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.663271427154541},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5195348858833313},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.46417853236198425},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.4624491035938263},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45854902267456055},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.44404345750808716},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.386135071516037},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37392115592956543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001763224601746},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7843308448791504},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7758304476737976},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6898412704467773},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.663271427154541},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5195348858833313},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.46417853236198425},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.4624491035938263},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45854902267456055},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.44404345750808716},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.386135071516037},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37392115592956543},{"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:10.1109/cmpsac.2003.1245399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cmpsac.2003.1245399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1659541576","https://openalex.org/W2003000928","https://openalex.org/W2006119904","https://openalex.org/W2029341294","https://openalex.org/W2058374187","https://openalex.org/W2079672501","https://openalex.org/W2089192108","https://openalex.org/W2138621811","https://openalex.org/W2156093156","https://openalex.org/W2165696355","https://openalex.org/W4210407477","https://openalex.org/W4240407914","https://openalex.org/W6683142088","https://openalex.org/W6684349482"],"related_works":["https://openalex.org/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W2980544443","https://openalex.org/W2419328283","https://openalex.org/W1770021664","https://openalex.org/W2389041382","https://openalex.org/W2964491004","https://openalex.org/W2070988406","https://openalex.org/W2223855511","https://openalex.org/W2296228743"],"abstract_inverted_index":{"Topic-specific":[0],"search":[1,9,18],"engines":[2,19],"that":[3],"offer":[4],"users":[5],"relevant":[6],"topics":[7,45],"as":[8,72],"results":[10,97],"have":[11],"recently":[12],"been":[13],"developed.":[14],"However,":[15],"these":[16,81],"topic-specific":[17],"require":[20],"intensive":[21],"human":[22],"efforts":[23],"to":[24,107],"build":[25],"and":[26,75,91,98],"maintain.":[27],"In":[28,35],"addition,":[29],"they":[30],"visit":[31],"many":[32],"irrelevant":[33],"pages.":[34],"our":[36,112],"project,":[37],"we":[38,48,63,84],"propose":[39],"a":[40],"new":[41],"approach":[42],"for":[43,52,77],"Web":[44],"search.":[46],"First,":[47],"do":[49],"early":[50],"detection":[51],"\"candidate":[53],"topics\"":[54],"while":[55],"extracting":[56],"words":[57],"from":[58],"the":[59,68,96,99,109],"HTML":[60],"text.":[61],"Secondly,":[62],"perform":[64],"data":[65],"analysis":[66],"on":[67],"appearance":[69,73],"information":[70],"such":[71],"times":[74,90],"places":[76],"candidate":[78,87],"topics.":[79],"By":[80],"two":[82],"techniques,":[83],"can":[85],"reduce":[86],"topics'":[88],"crawling":[89],"computing":[92],"cost.":[93],"Analysis":[94],"of":[95,111],"comparisons":[100],"with":[101],"related":[102],"research":[103],"will":[104],"be":[105],"made":[106],"demonstrate":[108],"effectiveness":[110],"approach.":[113]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}