{"id":"https://openalex.org/W4392845318","doi":"https://doi.org/10.1145/3625007.3627305","title":"Modelling Text Similarity: A Survey","display_name":"Modelling Text Similarity: A Survey","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4392845318","doi":"https://doi.org/10.1145/3625007.3627305"},"language":"en","primary_location":{"id":"doi:10.1145/3625007.3627305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625007.3627305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625007.3627305","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3625007.3627305","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029428223","display_name":"Wenchuan Mu","orcid":"https://orcid.org/0009-0007-2395-9731"},"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":"Wenchuan Mu","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0007-2395-9731","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, 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, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4569-0901","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029428223"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":1.0225,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8208737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.657698392868042},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5964338183403015},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43665748834609985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39346060156822205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3484799265861511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.657698392868042},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5964338183403015},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43665748834609985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39346060156822205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3484799265861511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625007.3627305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625007.3627305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625007.3627305","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625007.3627305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625007.3627305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625007.3627305","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392845318.pdf"},"referenced_works_count":106,"referenced_works":["https://openalex.org/W20811212","https://openalex.org/W41404523","https://openalex.org/W93922237","https://openalex.org/W113724690","https://openalex.org/W1489409710","https://openalex.org/W1494404649","https://openalex.org/W1587871245","https://openalex.org/W1603508585","https://openalex.org/W1614298861","https://openalex.org/W1647671624","https://openalex.org/W1647729745","https://openalex.org/W1748393397","https://openalex.org/W1843891098","https://openalex.org/W1942015218","https://openalex.org/W1956340063","https://openalex.org/W1964808688","https://openalex.org/W1970264778","https://openalex.org/W1981617416","https://openalex.org/W1985697096","https://openalex.org/W1994790623","https://openalex.org/W2034790838","https://openalex.org/W2057332882","https://openalex.org/W2060505622","https://openalex.org/W2100935296","https://openalex.org/W2104246439","https://openalex.org/W2104858828","https://openalex.org/W2117805756","https://openalex.org/W2120779048","https://openalex.org/W2121135610","https://openalex.org/W2122865749","https://openalex.org/W2123724244","https://openalex.org/W2127128140","https://openalex.org/W2131744502","https://openalex.org/W2133564696","https://openalex.org/W2141599568","https://openalex.org/W2149327368","https://openalex.org/W2149393279","https://openalex.org/W2153579005","https://openalex.org/W2164441316","https://openalex.org/W2165979181","https://openalex.org/W2170682101","https://openalex.org/W2250254985","https://openalex.org/W2250387780","https://openalex.org/W2250645967","https://openalex.org/W2251251208","https://openalex.org/W2251367463","https://openalex.org/W2252211741","https://openalex.org/W2280395961","https://openalex.org/W2413794162","https://openalex.org/W2469060249","https://openalex.org/W2493916176","https://openalex.org/W2507974895","https://openalex.org/W2523199059","https://openalex.org/W2552464009","https://openalex.org/W2574026469","https://openalex.org/W2605035112","https://openalex.org/W2612953412","https://openalex.org/W2751762827","https://openalex.org/W2758506174","https://openalex.org/W2784841940","https://openalex.org/W2786464815","https://openalex.org/W2887097088","https://openalex.org/W2888812214","https://openalex.org/W2892788670","https://openalex.org/W2895708641","https://openalex.org/W2896457183","https://openalex.org/W2900762555","https://openalex.org/W2902215807","https://openalex.org/W2903376039","https://openalex.org/W2936695845","https://openalex.org/W2941206741","https://openalex.org/W2949611393","https://openalex.org/W2953287808","https://openalex.org/W2966292672","https://openalex.org/W2969068412","https://openalex.org/W2970325945","https://openalex.org/W2970771982","https://openalex.org/W2970785793","https://openalex.org/W2974875810","https://openalex.org/W3021989929","https://openalex.org/W3090556797","https://openalex.org/W3104033643","https://openalex.org/W3119505375","https://openalex.org/W3144078281","https://openalex.org/W4297787787","https://openalex.org/W6621906925","https://openalex.org/W6639619044","https://openalex.org/W6647036627","https://openalex.org/W6681698864","https://openalex.org/W6682631176","https://openalex.org/W6683895063","https://openalex.org/W6684147746","https://openalex.org/W6684406844","https://openalex.org/W6691431627","https://openalex.org/W6691649953","https://openalex.org/W6725530328","https://openalex.org/W6729651007","https://openalex.org/W6736893582","https://openalex.org/W6739901393","https://openalex.org/W6749583565","https://openalex.org/W6751685368","https://openalex.org/W6754654208","https://openalex.org/W6761205521","https://openalex.org/W6782529094","https://openalex.org/W6790845975","https://openalex.org/W6898505805"],"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/W3204019825"],"abstract_inverted_index":{"Online":[0],"social":[1,88],"networking":[2,89],"services":[3],"such":[4,40],"as":[5,34,36,41,189],"Twitter":[6],"and":[7,32,58,67,76,96,101,112,128,168,182],"Instagram":[8],"have":[9],"become":[10],"pervasive":[11],"platforms":[12,24],"for":[13,64,161,193],"engaging":[14],"in":[15,83,197],"discussions":[16],"on":[17,51,135],"a":[18,151,190],"wide":[19],"array":[20],"of":[21,47,78,86,109,139,154,170,202],"topics.":[22],"These":[23],"cater":[25],"to":[26,56,99,149],"both":[27],"mainstream":[28],"subjects,":[29],"like":[30],"music":[31],"movies,":[33],"well":[35],"more":[37],"specialized":[38],"areas,":[39],"politics.":[42],"With":[43],"the":[44,54,74,84,94,107,136,155,166,195,199],"growing":[45],"volume":[46],"textual":[48],"data":[49],"generated":[50],"these":[52,171],"platforms,":[53],"ability":[55],"define":[57,100],"identify":[59],"similar":[60],"texts":[61],"becomes":[62],"crucial":[63],"effective":[65],"investigation":[66],"clustering.":[68],"In":[69],"this":[70,186],"paper,":[71],"we":[72,115],"explore":[73],"challenges":[75],"significance":[77],"text":[79,117,162,203],"similarity":[80,118,140],"regression":[81,119],"models":[82,120],"context":[85],"online":[87],"services.":[90],"We":[91,184],"delve":[92],"into":[93,121],"methods":[95,160],"techniques":[97],"employed":[98],"find":[102],"similarities":[103],"among":[104],"texts,":[105],"enabling":[106],"extraction":[108],"meaningful":[110],"patterns":[111],"insights.":[113],"Specifically,":[114],"categorize":[116],"four":[122],"distinct":[123],"types:":[124],"set-theoretic,":[125],"sequence-theoretic,":[126],"real-vector,":[127],"end-to-end":[129],"methods.":[130],"This":[131],"categorization":[132],"is":[133],"based":[134],"mathematical":[137],"formalisation":[138],"used":[141],"by":[142],"each":[143],"model.":[144],"Ultimately,":[145],"our":[146],"survey":[147,187],"aims":[148],"provide":[150],"comprehensive":[152],"overview":[153],"interlinkages":[156],"between":[157],"independently":[158],"proposed":[159],"similarity.":[163,204],"By":[164],"understanding":[165],"strengths":[167],"weaknesses":[169],"methods,":[172],"researchers":[173],"can":[174],"make":[175],"informed":[176],"decisions":[177],"when":[178],"designing":[179],"novel":[180],"approaches":[181],"algorithms.":[183],"hope":[185],"serves":[188],"valuable":[191],"resource":[192],"advancing":[194],"state-of-the-art":[196],"addressing":[198],"complex":[200],"problem":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}