{"id":"https://openalex.org/W2025422739","doi":"https://doi.org/10.1145/2644866.2644895","title":"SimSeerX","display_name":"SimSeerX","publication_year":2014,"publication_date":"2014-09-16","ids":{"openalex":"https://openalex.org/W2025422739","doi":"https://doi.org/10.1145/2644866.2644895","mag":"2025422739"},"language":"en","primary_location":{"id":"doi:10.1145/2644866.2644895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","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/A5108439761","display_name":"Kyle Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Williams","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108439761"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.636,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87043133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9993000030517578,"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":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234130144119263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8057920932769775},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6551697254180908},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5843823552131653},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5255737900733948},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.506995439529419},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4794817864894867},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.47459834814071655},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.4533866345882416},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4326796531677246},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19056302309036255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11093035340309143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234130144119263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8057920932769775},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6551697254180908},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5843823552131653},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5255737900733948},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.506995439529419},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4794817864894867},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.47459834814071655},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.4533866345882416},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4326796531677246},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19056302309036255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11093035340309143},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2644866.2644895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8251020264","display_name":null,"funder_award_id":"1143921","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W197093853","https://openalex.org/W1966427115","https://openalex.org/W1967612698","https://openalex.org/W2011501238","https://openalex.org/W2012833704","https://openalex.org/W2021947911","https://openalex.org/W2026961318","https://openalex.org/W2031169004","https://openalex.org/W2042641525","https://openalex.org/W2060636190","https://openalex.org/W2085922539","https://openalex.org/W2143296909","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W6607922304"],"related_works":["https://openalex.org/W4287126803","https://openalex.org/W3168266056","https://openalex.org/W4250737080","https://openalex.org/W2735162248","https://openalex.org/W2112890327","https://openalex.org/W311440260","https://openalex.org/W1971922616","https://openalex.org/W3145472249","https://openalex.org/W2127423266","https://openalex.org/W3172154474"],"abstract_inverted_index":{"The":[0],"need":[1],"to":[2,22,65,74],"find":[3,23],"similar":[4,24,47,62],"documents":[5,25,36,53],"occurs":[6],"in":[7,12],"many":[8],"settings,":[9],"such":[10],"as":[11,37,54],"plagiarism":[13],"detection":[14],"or":[15],"research":[16],"paper":[17,40],"recommendation.":[18],"Manually":[19],"constructing":[20],"queries":[21,55],"may":[26],"be":[27],"overly":[28],"complex,":[29],"thus":[30],"motivating":[31],"the":[32,66,85],"use":[33],"of":[34,61,68,89,106],"whole":[35,52],"queries.":[38],"This":[39],"introduces":[41],"SimSeerX,":[42,90],"a":[43,58,104],"search":[44],"engine":[45],"for":[46],"document":[48,81],"retrieval":[49],"that":[50,71],"receives":[51],"and":[56,80,87,99],"returns":[57],"ranked":[59],"list":[60],"documents.":[63,110],"Key":[64],"design":[67],"SimSeerX":[69],"is":[70,72],"able":[73],"work":[75],"with":[76,94],"multiple":[77],"similarity":[78,97],"functions":[79,98],"collections.":[82],"We":[83],"present":[84],"architecture":[86],"interface":[88],"show":[91],"its":[92,101],"applicability":[93],"3":[95],"different":[96],"demonstrate":[100],"scalability":[102],"on":[103],"collection":[105],"3.5":[107],"million":[108],"academic":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}