{"id":"https://openalex.org/W2217348016","doi":"https://doi.org/10.1109/bigdata.2015.7363995","title":"Sparsity adjusted information gain for feature selection in sentiment analysis","display_name":"Sparsity adjusted information gain for feature selection in sentiment analysis","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2217348016","doi":"https://doi.org/10.1109/bigdata.2015.7363995","mag":"2217348016"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5037918860","display_name":"Betty Ong","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"B. Y. Ong","raw_affiliation_strings":["A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore","institution_ids":["https://openalex.org/I4210091207","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102704405","display_name":"so-jin Goh","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"S. W. Goh","raw_affiliation_strings":["A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore","institution_ids":["https://openalex.org/I4210091207","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026897684","display_name":"Chi Xu","orcid":"https://orcid.org/0000-0002-5301-9376"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chi Xu","raw_affiliation_strings":["A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR, Planning and Operations Management Group Singapore Institute of Manufacturing Technology (SIMTech), Singapore, Singapore","institution_ids":["https://openalex.org/I4210091207","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"2122","last_page":"2128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998999834060669,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998999834060669,"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":0.9926999807357788,"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":0.9810000061988831,"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":0.7683998346328735},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7526065111160278},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.626335084438324},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5721345543861389},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5361098647117615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5257875919342041},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4933377802371979},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4595578610897064},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4588966369628906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44602835178375244},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.431837797164917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4213395118713379},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4192478358745575},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0963532030582428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683998346328735},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7526065111160278},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.626335084438324},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5721345543861389},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5361098647117615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257875919342041},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4933377802371979},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4595578610897064},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4588966369628906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44602835178375244},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.431837797164917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4213395118713379},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4192478358745575},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0963532030582428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334747","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1743243001","https://openalex.org/W1973637371","https://openalex.org/W2059099627","https://openalex.org/W2061873838","https://openalex.org/W2067624665","https://openalex.org/W2103333826","https://openalex.org/W2108150588","https://openalex.org/W2108646579","https://openalex.org/W2138665867","https://openalex.org/W2155925556","https://openalex.org/W2156741031","https://openalex.org/W2185688580","https://openalex.org/W2435251607","https://openalex.org/W2998216295","https://openalex.org/W4211186029","https://openalex.org/W4285719527","https://openalex.org/W4312808911","https://openalex.org/W6637805623","https://openalex.org/W6675969814","https://openalex.org/W6683381688","https://openalex.org/W6686653033","https://openalex.org/W6717827561","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W20047544","https://openalex.org/W3089231081"],"abstract_inverted_index":{"The":[0,200],"widespread":[1],"use":[2,191],"of":[3,48,59,96,108,114,122,129,131,183,212],"social":[4,36],"media":[5,37],"and":[6,28,42,104,171],"the":[7,46,100,127,166,175,181,184,210],"internet":[8],"are":[9,55,75],"emerging":[10],"trends":[11],"that":[12,64,204],"offer":[13],"an":[14,150],"additional":[15],"interaction":[16],"channel":[17],"for":[18,81,134],"companies":[19],"to":[20,89,98,119,173,180,190,194,208],"better":[21],"understand":[22],"customer":[23,40],"sentiments":[24],"about":[25],"their":[26],"brands":[27],"products.":[29],"Sentiment":[30],"analysis":[31],"uses":[32],"text":[33,70,135],"data":[34],"from":[35,68],"such":[38],"as":[39,156],"comments":[41],"reviews,":[43],"which":[44,73,164],"has":[45],"nature":[47],"high":[49],"dimensionality.":[50],"Without":[51],"selection,":[52],"typically":[53],"there":[54,74],"at":[56],"least":[57],"thousands":[58],"features":[60,80,97,139,193],"(words":[61],"or":[62,78],"phrases)":[63],"can":[65],"be":[66],"extracted":[67],"a":[69,91,144,196],"corpus,":[71],"among":[72],"many":[76,138],"redundant":[77],"irrelevant":[79],"sentiment":[82,213],"classification":[83,109],"task.":[84],"Thus,":[85],"it":[86],"is":[87,117,162,188,206],"critical":[88],"select":[90],"compact":[92],"yet":[93],"effective":[94],"set":[95],"avoid":[99],"complex":[101],"classifier":[102],"design":[103],"slow":[105],"running":[106],"time":[107],"process.":[110],"However,":[111],"very":[112],"few":[113,145],"existing":[115],"metrics":[116],"able":[118,189,207],"improve":[120,209],"efficacy":[121],"feature":[123,132,152,176,185],"selection":[124,153],"by":[125],"addressing":[126],"issue":[128],"sparsity":[130,157,182],"matrix":[133],"data,":[136],"i.e.,":[137],"may":[140],"appear":[141],"only":[142],"in":[143],"documents.":[146],"In":[147],"this":[148],"paper,":[149],"improved":[151],"metric":[154,170],"known":[155],"adjusted":[158],"information":[159,168],"gain":[160,169],"(SAIG)":[161],"proposed,":[163],"modifies":[165],"conventional":[167],"aims":[172],"adjust":[174],"ranking":[177],"scores":[178],"according":[179],"vector.":[186],"It":[187],"less":[192],"obtain":[195],"targeted":[197],"performance":[198,211],"level.":[199],"experiment":[201],"results":[202],"show":[203],"SAIG":[205],"classification.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}