{"id":"https://openalex.org/W2124185477","doi":"https://doi.org/10.1109/iccit.2009.235","title":"Duplicate Detection in Documents and WebPages Using Improved Longest Common Subsequence and Documents Syntactical Structures","display_name":"Duplicate Detection in Documents and WebPages Using Improved Longest Common Subsequence and Documents Syntactical Structures","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2124185477","doi":"https://doi.org/10.1109/iccit.2009.235","mag":"2124185477"},"language":"en","primary_location":{"id":"doi:10.1109/iccit.2009.235","doi":"https://doi.org/10.1109/iccit.2009.235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccit.2009.235","pdf_url":null,"source":{"id":"https://openalex.org/S4306419266","display_name":"International Conference on Computer Sciences and Convergence Information Technology","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Fourth International Conference on Computer Sciences and Convergence Information Technology","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5016133569","display_name":"Mohamed Elhadi","orcid":"https://orcid.org/0000-0002-7966-7224","observed_orcids":["https://orcid.org/0000-0002-7966-7224"]},"institutions":[{"id":"https://openalex.org/I47818738","display_name":"Sultan Qaboos University","ror":"https://ror.org/04wq8zb47","country_code":"OM","type":"education","lineage":["https://openalex.org/I47818738"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Mohamed Elhadi","raw_affiliation_strings":["Department of Computer Science, Sultan Qaboos University, Oman","Dept. of Comput. Sci., Sultan Qaboos Univ., Muscat, Oman"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sultan Qaboos University, Oman","institution_ids":["https://openalex.org/I47818738"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Sultan Qaboos Univ., Muscat, Oman","institution_ids":["https://openalex.org/I47818738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066917894","display_name":"Amjad Al-Tobi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47818738","display_name":"Sultan Qaboos University","ror":"https://ror.org/04wq8zb47","country_code":"OM","type":"education","lineage":["https://openalex.org/I47818738"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Amjad Al-Tobi","raw_affiliation_strings":["Center of Educational Technology, Sultan Qaboos University, Oman","Center of Educ. Technol., Sultan Qaboos Univ., Muscat, Oman"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Educational Technology, Sultan Qaboos University, Oman","institution_ids":["https://openalex.org/I47818738"]},{"raw_affiliation_string":"Center of Educ. Technol., Sultan Qaboos Univ., Muscat, Oman","institution_ids":["https://openalex.org/I47818738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47818738"],"apc_list":null,"apc_paid":null,"fwci":5.4711,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95958303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"679","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7113999724388123,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7113999724388123,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.06369999796152115,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.06030000001192093,"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/duplicate-detection","display_name":"duplicate detection","score":0.859000027179718},{"id":"https://openalex.org/keywords/longest-common-subsequence","display_name":"longest common subsequence","score":0.8489999771118164},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.902999997138977},{"id":"https://openalex.org/keywords/syntactic-structure","display_name":"syntactic structure","score":0.6629999876022339},{"id":"https://openalex.org/keywords/text-similarity","display_name":"text similarity","score":0.8479999899864197},{"id":"https://openalex.org/keywords/document-representation","display_name":"document representation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/document-ranking","display_name":"document ranking","score":0.7059999704360962},{"id":"https://openalex.org/keywords/search-result-filtering","display_name":"search result filtering","score":0.7419999837875366},{"id":"https://openalex.org/keywords/web-pages","display_name":"web pages","score":0.5680000185966492}],"concepts":[{"id":"https://openalex.org/C120098539","wikidata":"https://www.wikidata.org/wiki/Q141001","display_name":"Longest common subsequence problem","level":2,"score":0.9608404636383057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618687152862549},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.698965311050415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6916649341583252},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5986559391021729},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.5805192589759827},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.547079861164093},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5101609230041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48507896065711975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47702428698539734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18201422691345215},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15077203512191772},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0650242269039154},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06187528371810913},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccit.2009.235","doi":"https://doi.org/10.1109/iccit.2009.235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccit.2009.235","pdf_url":null,"source":{"id":"https://openalex.org/S4306419266","display_name":"International Conference on Computer Sciences and Convergence Information Technology","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Fourth International Conference on Computer Sciences and Convergence Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W122475380","https://openalex.org/W1205346469","https://openalex.org/W1501099340","https://openalex.org/W1501468703","https://openalex.org/W1547082571","https://openalex.org/W1548843388","https://openalex.org/W1551773846","https://openalex.org/W1557168499","https://openalex.org/W1558382083","https://openalex.org/W1566018662","https://openalex.org/W1577737098","https://openalex.org/W1596691921","https://openalex.org/W1937758960","https://openalex.org/W1948141881","https://openalex.org/W1968197683","https://openalex.org/W2007842132","https://openalex.org/W2034052397","https://openalex.org/W2055043387","https://openalex.org/W2060951907","https://openalex.org/W2111295912","https://openalex.org/W2113937265","https://openalex.org/W2123767107","https://openalex.org/W2132880933","https://openalex.org/W2142384583","https://openalex.org/W2153390303","https://openalex.org/W2347007084","https://openalex.org/W2612423570"],"related_works":["https://openalex.org/W1975365430","https://openalex.org/W1546699310","https://openalex.org/W2581081811","https://openalex.org/W2113937265","https://openalex.org/W4322772507","https://openalex.org/W2748409741","https://openalex.org/W2405258824","https://openalex.org/W2464185094","https://openalex.org/W2551155096","https://openalex.org/W2561569695"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"on":[3],"experiments":[4],"performed":[5],"to":[6,50,54,61],"investigate":[7],"the":[8,25,58,62,81],"use":[9],"of":[10,14,29,64,83],"a":[11,40,52,77],"combined":[12],"part":[13],"speech":[15],"(POS)":[16],"and":[17,27,56,79],"an":[18],"improved":[19,45],"longest":[20],"common":[21],"subsequence":[22],"(LCS)":[23],"in":[24,72,80],"analysis":[26],"calculation":[28],"similarity":[30,63],"between":[31],"texts.":[32],"The":[33,68],"text's":[34],"syntactical":[35],"structures":[36],"were":[37,89],"used":[38],"as":[39],"representation":[41,53],"for":[42],"documents.":[43],"An":[44],"LCS":[46],"algorithm":[47],"was":[48,70],"applied":[49,71],"such":[51],"compare":[55],"rank":[57],"documents":[59,75],"according":[60],"their":[65],"representative":[66],"string.":[67],"approach":[69],"detecting":[73],"duplicate":[74],"within":[76],"corpus,":[78],"filtering":[82],"search":[84],"engine":[85],"results.":[86],"Results":[87],"obtained":[88],"encouraging.":[90]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
