{"id":"https://openalex.org/W3000110947","doi":"https://doi.org/10.1145/3368567.3368572","title":"Authorship Clustering using TF-IDF weighted Word-Embeddings","display_name":"Authorship Clustering using TF-IDF weighted Word-Embeddings","publication_year":2019,"publication_date":"2019-12-12","ids":{"openalex":"https://openalex.org/W3000110947","doi":"https://doi.org/10.1145/3368567.3368572","mag":"3000110947"},"language":"en","primary_location":{"id":"doi:10.1145/3368567.3368572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368567.3368572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"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/A5069767004","display_name":"Lucky Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lucky Agarwal","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, New Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069444808","display_name":"Kartik Thakral","orcid":"https://orcid.org/0000-0002-2528-9950"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kartik Thakral","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, New Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025455738","display_name":"Gaurav Bhatt","orcid":"https://orcid.org/0000-0002-0980-8765"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gaurav Bhatt","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068531665","display_name":"Ankush Mittal","orcid":"https://orcid.org/0000-0001-5987-2055"},"institutions":[{"id":"https://openalex.org/I60054993","display_name":"Graphic Era University","ror":"https://ror.org/03wqgqd89","country_code":"IN","type":"education","lineage":["https://openalex.org/I60054993"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankush Mittal","raw_affiliation_strings":["Graphic Era University Dehradun, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graphic Era University Dehradun, India","institution_ids":["https://openalex.org/I60054993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5466,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.72901259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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":0.9933000206947327,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9886000156402588,"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":0.8085308074951172},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.742692232131958},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6640432476997375},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.6443040370941162},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6250811815261841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6230967044830322},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6067631244659424},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5925827622413635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5234289169311523},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4898235499858856},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.39660871028900146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3472555875778198},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16719970107078552},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.08849829435348511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085308074951172},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.742692232131958},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6640432476997375},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.6443040370941162},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6250811815261841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230967044830322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6067631244659424},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5925827622413635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5234289169311523},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4898235499858856},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.39660871028900146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3472555875778198},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16719970107078552},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.08849829435348511},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368567.3368572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368567.3368572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2072240081","https://openalex.org/W2085487226","https://openalex.org/W2135345655","https://openalex.org/W2250539671","https://openalex.org/W2295585256","https://openalex.org/W2574538148","https://openalex.org/W2574619972","https://openalex.org/W2751155097","https://openalex.org/W2950577311","https://openalex.org/W2998704965","https://openalex.org/W6680532216"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800","https://openalex.org/W4385432812"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,24,94,111],"propose":[4],"a":[5,69],"novel":[6],"idea":[7],"to":[8,57,103],"solve":[9],"the":[10,33,37,43,48,53,66,73,96,100,114,122],"problem":[11],"of":[12,32,52],"Author":[13,20],"Clustering":[14],"which":[15,76],"is":[16],"introduced":[17],"in":[18,72,75],"PAN-2017":[19,104],"Identification":[21],"task.":[22,107,124],"First,":[23],"use":[25],"word":[26],"embeddings":[27],"that":[28,65,113],"brings":[29],"semantic":[30],"feature":[31],"words":[34,67],"along":[35],"with":[36,99],"grammatical":[38],"and":[39],"syntactic":[40],"information.":[41],"Secondly,":[42],"documents":[44,74,85],"are":[45,90],"represented":[46],"as":[47],"TF-IDF":[49,62],"weighted":[50],"sum":[51],"embedding":[54],"vectors":[55],"corresponding":[56],"each":[58,88],"word.":[59],"A":[60],"higher":[61],"weight":[63],"implies":[64],"have":[68],"stronger":[70],"relationship":[71],"they":[77],"appear.":[78],"Lastly,":[79],"using":[80],"hierarchical":[81],"clustering":[82,106],"all":[83],"those":[84],"written":[86],"by":[87],"author":[89,105],"grouped":[91],"together.":[92],"Finally,":[93],"compare":[95],"proposed":[97,115],"technique":[98,116],"top":[101],"submissions":[102],"Through":[108],"extensive":[109],"experimentation,":[110],"show":[112],"outperforms":[117],"various":[118],"state-of-the-art":[119],"models":[120],"on":[121],"given":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}
