{"id":"https://openalex.org/W2809503151","doi":"https://doi.org/10.1109/icatcct.2017.8389161","title":"san_sim: Factual and efficient URL text similarity algorithm","display_name":"san_sim: Factual and efficient URL text similarity algorithm","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2809503151","doi":"https://doi.org/10.1109/icatcct.2017.8389161","mag":"2809503151"},"language":"en","primary_location":{"id":"doi:10.1109/icatcct.2017.8389161","doi":"https://doi.org/10.1109/icatcct.2017.8389161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icatcct.2017.8389161","pdf_url":null,"source":{"id":"https://openalex.org/S4306423279","display_name":"International Conference on Applied and Theoretical Computing and Communication 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":"2017 3rd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5000099400","display_name":"Dr Sandhya Pundhir","orcid":"https://orcid.org/0000-0002-1793-4876","observed_orcids":["https://orcid.org/0000-0002-1793-4876"]},"institutions":[{"id":"https://openalex.org/I105454292","display_name":"Guru Gobind Singh Indraprastha University","ror":"https://ror.org/034q1za58","country_code":"IN","type":"education","lineage":["https://openalex.org/I105454292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandhya","raw_affiliation_strings":["Scholar USICT GGSIPU, Dwarka Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scholar USICT GGSIPU, Dwarka Delhi, India","institution_ids":["https://openalex.org/I105454292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049855020","display_name":"Udayan Ghose","orcid":"https://orcid.org/0000-0002-2438-0082","observed_orcids":["https://orcid.org/0000-0002-2438-0082"]},"institutions":[{"id":"https://openalex.org/I105454292","display_name":"Guru Gobind Singh Indraprastha University","ror":"https://ror.org/034q1za58","country_code":"IN","type":"education","lineage":["https://openalex.org/I105454292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Udayan Ghose","raw_affiliation_strings":["Professor USICT GGSIPU, Dwarka Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Professor USICT GGSIPU, Dwarka Delhi, India","institution_ids":["https://openalex.org/I105454292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I105454292"],"apc_list":null,"apc_paid":null,"fwci":0.3585,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49570836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.5981000065803528,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.5981000065803528,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.30809998512268066,"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/T11269","display_name":"Algorithms and Data Compression","score":0.017799999564886093,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page-relevance","display_name":"web page relevance","score":0.421999990940094},{"id":"https://openalex.org/keywords/content-mining","display_name":"content mining","score":0.7250000238418579},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.9419999718666077},{"id":"https://openalex.org/keywords/longest-common-subsequence","display_name":"longest common subsequence","score":0.8309999704360962},{"id":"https://openalex.org/keywords/dice-similarity-coefficient","display_name":"Dice coefficient","score":0.7760000228881836},{"id":"https://openalex.org/keywords/web-mining","display_name":"web mining","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875570058822632},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.743414044380188},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.7303781509399414},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6154327988624573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5854921340942383},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5719197988510132},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.48664817214012146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4694368839263916},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42470860481262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4132847487926483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361586332321167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3290981352329254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15193918347358704},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13197922706604004},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09035506844520569},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icatcct.2017.8389161","doi":"https://doi.org/10.1109/icatcct.2017.8389161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icatcct.2017.8389161","pdf_url":null,"source":{"id":"https://openalex.org/S4306423279","display_name":"International Conference on Applied and Theoretical Computing and Communication 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":"2017 3rd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W910013450","https://openalex.org/W1769946858","https://openalex.org/W1902530683","https://openalex.org/W2004879117","https://openalex.org/W2140655242","https://openalex.org/W2171313960","https://openalex.org/W2463592278","https://openalex.org/W2607793743","https://openalex.org/W2613669284"],"related_works":["https://openalex.org/W7122231","https://openalex.org/W29468053","https://openalex.org/W2151148646","https://openalex.org/W2566821273","https://openalex.org/W4403615210","https://openalex.org/W2374283646","https://openalex.org/W1573190978","https://openalex.org/W1973416695","https://openalex.org/W1980763532","https://openalex.org/W7095879809"],"abstract_inverted_index":{"Similarity":[0],"determines":[1],"the":[2,15,37,52,96],"relation":[3],"between":[4,14],"two":[5,16,25],"objects.":[6],"We":[7,89],"need":[8],"this":[9],"to":[10,23,36],"establish":[11],"an":[12],"order":[13],"objects":[17],"being":[18],"compared.":[19],"Here":[20,72],"we":[21],"want":[22],"compare":[24],"URLs":[26],"(Uniform":[27],"Resource":[28],"Locater)":[29],"and":[30,80,107,121],"find":[31,90],"which":[32,48],"is":[33,42,57,83,115],"more":[34],"relevant":[35],"input":[38],"query.":[39],"Content":[40],"mining":[41,46],"one":[43],"of":[44,51,69,111],"web":[45,53],"technique":[47],"uses":[49],"text":[50,75],"page.":[54],"Online":[55],"learning":[56,134],"used":[58,64,137],"where":[59],"entire":[60],"dataset":[61],"cannot":[62],"be":[63],"at":[65],"training":[66],"time":[67],"because":[68],"its":[70],"size.":[71],"few":[73],"popular":[74],"similarity":[76,99],"methods":[77],"are":[78,124],"implemented":[79],"their":[81],"relevance":[82],"compared":[84],"with":[85,138],"our":[86,92,112],"proposed":[87,113],"method.":[88],"that":[91,128],"algo-rithmperforms":[93],"better":[94,116,142],"than":[95],"traditional":[97],"tex":[98],"measures":[100,123],"such":[101],"as":[102,117],"LCS":[103],"(Longest":[104],"Common":[105],"Sequence)":[106],"Dice":[108],"score.":[109],"Performance":[110],"method":[114,140],"higher":[118],"Precision,":[119],"Recall":[120],"F":[122],"achieved.":[125],"This":[126],"proves":[127],"data":[129],"specific":[130],"filtering":[131],"methods,":[132],"online":[133],"principles":[135],"when":[136],"statistical":[139],"produces":[141],"result.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-29T00:00:00"}