{"id":"https://openalex.org/W4411624583","doi":"https://doi.org/10.1145/3703323.3703698","title":"Imbalanced Multi-Class Research Article Classification using Sentence Transformers and Machine Learning Algorithms","display_name":"Imbalanced Multi-Class Research Article Classification using Sentence Transformers and Machine Learning Algorithms","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4411624583","doi":"https://doi.org/10.1145/3703323.3703698"},"language":"en","primary_location":{"id":"doi:10.1145/3703323.3703698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703698","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3703323.3703698","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117292107","display_name":"Saliq Gowhar","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Saliq Gowhar","raw_affiliation_strings":["Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India"],"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118622688","display_name":"Praveen Kempaiah","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Kempaiah","raw_affiliation_strings":["Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India"],"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085977948","display_name":"S. Sowmya Kamath","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sowmya Kamath S","raw_affiliation_strings":["Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India"],"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080285200","display_name":"Vijayan Sugumaran","orcid":"https://orcid.org/0000-0003-2557-3182"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayan Sugumaran","raw_affiliation_strings":["Department of Decision and Information Sciences, Oakland University, Rochester, Michigan, USA"],"affiliations":[{"raw_affiliation_string":"Department of Decision and Information Sciences, Oakland University, Rochester, Michigan, USA","institution_ids":["https://openalex.org/I177721651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5117292107"],"corresponding_institution_ids":["https://openalex.org/I11880225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2788409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9934999942779541,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9934999942779541,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9919000267982483,"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":0.9740999937057495,"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":0.7139534950256348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661733746528625},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5182178616523743},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.5114135146141052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5081772804260254},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48271915316581726},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46516159176826477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33899521827697754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139534950256348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661733746528625},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5182178616523743},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.5114135146141052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5081772804260254},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48271915316581726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46516159176826477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33899521827697754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703323.3703698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703698","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3703323.3703698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703323.3703698","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2909182718","https://openalex.org/W3008374555","https://openalex.org/W3013631884","https://openalex.org/W3016473712","https://openalex.org/W3095836434","https://openalex.org/W3099847344","https://openalex.org/W3125892802"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W3213683101","https://openalex.org/W3035095237","https://openalex.org/W3186233728","https://openalex.org/W4200459988","https://openalex.org/W4361733776","https://openalex.org/W4281776617","https://openalex.org/W2908849530","https://openalex.org/W4398756457"],"abstract_inverted_index":{"Categorizing":[0],"scientific":[1],"articles":[2,51],"into":[3,52],"specific":[4],"research":[5],"fields":[6],"is":[7,75],"a":[8],"challenging":[9],"problem,":[10],"considering":[11],"the":[12,30,57,88,108],"volume":[13],"and":[14,83,105],"variety":[15],"of":[16,66,103],"published":[17],"literature.":[18],"However,":[19],"existing":[20],"classification":[21],"systems":[22],"often":[23],"suffer":[24],"from":[25],"limitations":[26],"regarding":[27],"taxonomy":[28],"or":[29],"models":[31],"used":[32],"for":[33,71],"classification.":[34],"This":[35],"article":[36],"explores":[37],"approaches":[38],"built":[39],"on":[40,94],"Sentence":[41],"Transformer":[42],"embeddings":[43,97],"combined":[44],"with":[45,56,80,98],"Machine":[46],"Learning":[47],"algorithms":[48],"to":[49],"classify":[50],"123":[53],"predefined":[54],"classes,":[55],"dataset":[58],"being":[59],"heavily":[60],"imbalanced":[61],"in":[62],"nature.":[63],"The":[64,85],"effectiveness":[65],"Large":[67],"Language":[68],"Models":[69],"(LLMs)":[70],"generating":[72],"synthetic":[73],"data":[74],"also":[76],"experimented":[77],"with,":[78],"along":[79],"synonym":[81],"augmentation":[82],"SMOTE.":[84],"best-performing":[86],"model,":[87],"One":[89],"vs":[90],"Rest":[91],"classifier":[92],"trained":[93],"MP-Net":[95],"sentence":[96],"SMOTE,":[99],"achieved":[100],"an":[101],"accuracy":[102],"77%,":[104],"outperformed":[106],"all":[107],"other":[109],"models.":[110]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}