{"id":"https://openalex.org/W4226041275","doi":"https://doi.org/10.1109/bigdata52589.2021.9671598","title":"Analyzing Scientific Publications using Domain-Specific Word Embedding and Topic Modelling","display_name":"Analyzing Scientific Publications using Domain-Specific Word Embedding and Topic Modelling","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4226041275","doi":"https://doi.org/10.1109/bigdata52589.2021.9671598"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE International Conference on Big Data (Big Data)","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/A5067002888","display_name":"Trisha Singhal","orcid":"https://orcid.org/0000-0003-3880-789X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Trisha Singhal","raw_affiliation_strings":["Singapore University of Technology and Design,SUTD-MIT International Design Centre,Singapore","SUTD-MIT International Design Centre, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,SUTD-MIT International Design Centre,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"SUTD-MIT International Design Centre, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741943","display_name":"Junhua Liu","orcid":"https://orcid.org/0000-0003-4477-7439"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junhua Liu","raw_affiliation_strings":["Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore","Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067484594","display_name":"Luci\u00ebnne Blessing","orcid":"https://orcid.org/0000-0001-9612-1357"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lucienne T. M. Blessing","raw_affiliation_strings":["Singapore University of Technology and Design,Engineering Product Development Pillar,Singapore","Engineering Product Development Pillar, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Engineering Product Development Pillar,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005406384","display_name":"Kwan Hui Lim","orcid":"https://orcid.org/0000-0002-4569-0901"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kwan Hui Lim","raw_affiliation_strings":["Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore","Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067002888"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.7613,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75926439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"4965","last_page":"4973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9962999820709229,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.7711972594261169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367516160011292},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6730682849884033},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6380550861358643},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.567569375038147},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.5584737062454224},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5396817326545715},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5274660587310791},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5178066492080688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5074378848075867},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4622945487499237},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4612855315208435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40330129861831665},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3941101133823395},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14848148822784424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13063105940818787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10495805740356445}],"concepts":[{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.7711972594261169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367516160011292},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6730682849884033},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6380550861358643},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.567569375038147},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.5584737062454224},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5396817326545715},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5274660587310791},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5178066492080688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5074378848075867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4622945487499237},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4612855315208435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40330129861831665},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3941101133823395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14848148822784424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13063105940818787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10495805740356445},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1559499673","https://openalex.org/W1603719052","https://openalex.org/W1614298861","https://openalex.org/W1978394996","https://openalex.org/W1983981789","https://openalex.org/W1995111176","https://openalex.org/W2079525773","https://openalex.org/W2083867412","https://openalex.org/W2127218421","https://openalex.org/W2130339025","https://openalex.org/W2133564696","https://openalex.org/W2157444450","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2416987009","https://openalex.org/W2499202522","https://openalex.org/W2501715334","https://openalex.org/W2577020101","https://openalex.org/W2617241599","https://openalex.org/W2626654956","https://openalex.org/W2795398890","https://openalex.org/W2886735965","https://openalex.org/W2896457183","https://openalex.org/W2949488362","https://openalex.org/W2958860733","https://openalex.org/W2959758064","https://openalex.org/W2962739339","https://openalex.org/W2964346820","https://openalex.org/W2966696991","https://openalex.org/W2972253866","https://openalex.org/W3008695043","https://openalex.org/W3034489696","https://openalex.org/W3037793211","https://openalex.org/W3081243492","https://openalex.org/W3081987387","https://openalex.org/W3105111366","https://openalex.org/W3137361708","https://openalex.org/W3145795540","https://openalex.org/W3152898658","https://openalex.org/W3173655645","https://openalex.org/W3195868363","https://openalex.org/W4231510805","https://openalex.org/W4235720003","https://openalex.org/W4253723135","https://openalex.org/W4297662601","https://openalex.org/W4300081969","https://openalex.org/W4367858557","https://openalex.org/W4385682194","https://openalex.org/W6633305578","https://openalex.org/W6635969143","https://openalex.org/W6636510571","https://openalex.org/W6639619044","https://openalex.org/W6678914141","https://openalex.org/W6679434410","https://openalex.org/W6679482899","https://openalex.org/W6683161245","https://openalex.org/W6727255303","https://openalex.org/W6729269041","https://openalex.org/W6732789214","https://openalex.org/W6755207826","https://openalex.org/W6758993734","https://openalex.org/W6765764332","https://openalex.org/W6765837245","https://openalex.org/W6777012294","https://openalex.org/W6843709333"],"related_works":["https://openalex.org/W2386723501","https://openalex.org/W2387879414","https://openalex.org/W2390304029","https://openalex.org/W2354923724","https://openalex.org/W2146830340","https://openalex.org/W2377101853","https://openalex.org/W2362180844","https://openalex.org/W2105573916","https://openalex.org/W2378405797","https://openalex.org/W4286432911"],"abstract_inverted_index":{"The":[0],"scientific":[1,29,78],"world":[2],"is":[3,35,65,108],"changing":[4],"a":[5,25,158],"tarapid":[6],"pace,":[7],"with":[8],"new":[9,14],"technology":[10],"being":[11,16],"developed":[12],"and":[13,41,48,60,84,129,146],"trends":[15,40],"set":[17],"at":[18],"an":[19],"increasing":[20],"frequency.":[21],"This":[22,45],"paper":[23],"presents":[24],"framework":[26,46],"for":[27],"conducting":[28],"analyses":[30],"of":[31,52,71,90,94,113,126,160],"academic":[32],"publications,":[33],"which":[34,87],"crucial":[36],"to":[37,67,110,134,153],"monitor":[38],"research":[39,103,114,119,138],"identify":[42,111],"potential":[43],"innovations.":[44],"adopts":[47],"combines":[49],"various":[50,102],"techniques":[51],"Natural":[53],"Language":[54],"Processing,":[55],"such":[56],"as":[57,96,98],"word":[58],"embedding":[59,64],"topic":[61,106,164],"modelling.":[62],"Word":[63],"used":[66,109],"capture":[68],"semantic":[69,92],"meanings":[70,93],"domain-specific":[72,99],"words.":[73],"We":[74,121],"propose":[75],"two":[76,127,130,137],"novel":[77],"publication":[79],"embedding,":[80],"i.e.,":[81],"P":[82,85],"UB-G":[83],"UB-W,":[86],"are":[88,149],"capable":[89],"learning":[91],"general":[95],"well":[97],"words":[100],"in":[101,151],"fields.":[104,120],"Thereafter,":[105],"modelling":[107],"clusters":[112],"topics":[115],"within":[116],"these":[117],"larger":[118],"curated":[122],"apublication":[123],"dataset":[124],"consisting":[125],"conferences":[128],"journals":[131],"from":[132,136],"1995":[133],"2020":[135],"domains.":[139],"Experimental":[140],"results":[141],"show":[142],"that":[143],"our":[144],"PUB-G":[145],"PUB-W":[147],"embeddings":[148,156],"superior":[150],"comparison":[152],"other":[154],"baseline":[155],"by":[157],"margin":[159],"~0.18-1.03":[161],"based":[162],"on":[163],"coherence.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}