{"id":"https://openalex.org/W358099420","doi":"https://doi.org/10.1007/978-3-642-33290-6_22","title":"Identifying \u201cSoft 404\u201d Error Pages: Analyzing the Lexical Signatures of Documents in Distributed Collections","display_name":"Identifying \u201cSoft 404\u201d Error Pages: Analyzing the Lexical Signatures of Documents in Distributed Collections","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W358099420","doi":"https://doi.org/10.1007/978-3-642-33290-6_22","mag":"358099420"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-33290-6_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-33290-6_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5004987801","display_name":"Luis Javier Ulloa Meneses","orcid":"https://orcid.org/0000-0003-2941-5675"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luis Meneses","raw_affiliation_strings":["Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065474822","display_name":"Richard Furuta","orcid":"https://orcid.org/0000-0002-7349-4203"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Furuta","raw_affiliation_strings":["Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077860280","display_name":"Frank Shipman","orcid":"https://orcid.org/0009-0007-1469-9835"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Shipman","raw_affiliation_strings":["Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Center for the Study of Digital Libraries and Department of Computer Science and Engineering, Texas A&M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004987801"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.0438,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90890419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9930999875068665,"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/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.6510431170463562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34419822692871094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510431170463562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34419822692871094}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-33290-6_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-33290-6_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1485280201","https://openalex.org/W1622499492","https://openalex.org/W1969210271","https://openalex.org/W1969301668","https://openalex.org/W1973688760","https://openalex.org/W1985004975","https://openalex.org/W1985887722","https://openalex.org/W1988966845","https://openalex.org/W1995821742","https://openalex.org/W2017564581","https://openalex.org/W2021198451","https://openalex.org/W2025243215","https://openalex.org/W2039221734","https://openalex.org/W2040427982","https://openalex.org/W2048254579","https://openalex.org/W2049961212","https://openalex.org/W2051514640","https://openalex.org/W2054088120","https://openalex.org/W2076484470","https://openalex.org/W2111243605","https://openalex.org/W2117629987","https://openalex.org/W2142747917","https://openalex.org/W2148361904","https://openalex.org/W2151948168","https://openalex.org/W2153083299","https://openalex.org/W4237987539","https://openalex.org/W4255929443"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}