{"id":"https://openalex.org/W7083178799","doi":"https://doi.org/10.18421/sar83-01","title":"Profiling Noisy Social Media Data for Sentiment Applications: A Visual and Analytical Framework","display_name":"Profiling Noisy Social Media Data for Sentiment Applications: A Visual and Analytical Framework","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W7083178799","doi":"https://doi.org/10.18421/sar83-01"},"language":"en","primary_location":{"id":"doi:10.18421/sar83-01","doi":"https://doi.org/10.18421/sar83-01","is_oa":true,"landing_page_url":"https://doi.org/10.18421/sar83-01","pdf_url":"https://www.sarjournal.com/content/83/SARJournalSeptember2025_213_224.pdf","source":{"id":"https://openalex.org/S4210236062","display_name":"SAR Journal - Science and Research","issn_l":"2619-9955","issn":["2619-9955","2619-9963"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SAR Journal - Science and Research","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sarjournal.com/content/83/SARJournalSeptember2025_213_224.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069152224","display_name":"Daniela Pencheva","orcid":"https://orcid.org/0000-0002-0661-2177","observed_orcids":["https://orcid.org/0000-0002-0661-2177"]},"institutions":[{"id":"https://openalex.org/I124938932","display_name":"University of Economics Varna","ror":"https://ror.org/03g67sb77","country_code":"BG","type":"education","lineage":["https://openalex.org/I124938932"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Daniela Pencheva","raw_affiliation_strings":["Science and Research Institute, University of Economics - Varna, bul. Knyaz Boris I 77, Varna, Bulgaria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Research Institute, University of Economics - Varna, bul. Knyaz Boris I 77, Varna, Bulgaria","institution_ids":["https://openalex.org/I124938932"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069152224"],"corresponding_institution_ids":["https://openalex.org/I124938932"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37422131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0,"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/sentiment-analysis","display_name":"sentiment analysis","score":0.878000020980835},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.7039999961853027},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.621999979019165},{"id":"https://openalex.org/keywords/lexicon-based-sentiment-analysis","display_name":"lexicon-based sentiment analysis","score":0.7730000019073486},{"id":"https://openalex.org/keywords/emojis","display_name":"emojis","score":0.8999999761581421},{"id":"https://openalex.org/keywords/hashtags","display_name":"hashtags","score":0.9409999847412109},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.859000027179718},{"id":"https://openalex.org/keywords/business-intelligence-dashboard","display_name":"business intelligence dashboard","score":0.8209999799728394},{"id":"https://openalex.org/keywords/data-profiling","display_name":"data profiling","score":0.4970000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882999777793884},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.78329998254776},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6255000233650208},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4255000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3497999906539917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18421/sar83-01","doi":"https://doi.org/10.18421/sar83-01","is_oa":true,"landing_page_url":"https://doi.org/10.18421/sar83-01","pdf_url":"https://www.sarjournal.com/content/83/SARJournalSeptember2025_213_224.pdf","source":{"id":"https://openalex.org/S4210236062","display_name":"SAR Journal - Science and Research","issn_l":"2619-9955","issn":["2619-9955","2619-9963"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SAR Journal - Science and Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.18421/sar83-01","doi":"https://doi.org/10.18421/sar83-01","is_oa":true,"landing_page_url":"https://doi.org/10.18421/sar83-01","pdf_url":"https://www.sarjournal.com/content/83/SARJournalSeptember2025_213_224.pdf","source":{"id":"https://openalex.org/S4210236062","display_name":"SAR Journal - Science and Research","issn_l":"2619-9955","issn":["2619-9955","2619-9963"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SAR Journal - Science and Research","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7083178799.pdf","grobid_xml":"https://content.openalex.org/works/W7083178799.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,89,129],"practical":[4],"approach":[5,112],"for":[6,92,131],"analyzing":[7],"noisy":[8,75],"social":[9],"media":[10],"data":[11,52,60,108,135],"in":[12,104,115,134],"sentiment":[13,47,63,78,124],"analysis.":[14,125],"It":[15,126],"focuses":[16],"on":[17],"identifying":[18],"and":[19,32,50,69,80,94,106,117,121],"mitigating":[20],"the":[21,119],"impact":[22],"of":[23,123],"elements":[24],"such":[25],"as":[26],"emojis,":[27],"repeated":[28],"characters,":[29],"hashtags,":[30],"links,":[31],"informal":[33],"expressions,":[34],"which":[35],"often":[36],"distort":[37],"results.":[38],"A":[39],"simple":[40],"lexicon-based":[41],"method":[42],"is":[43,56,113],"applied":[44],"to":[45,57,83],"assess":[46],"both":[48],"before":[49],"after":[51],"cleansing.":[53],"The":[54,86,110],"objective":[55],"illustrate":[58],"how":[59,99],"quality":[61],"influences":[62],"interpretation,":[64],"supported":[65],"by":[66],"clear":[67],"examples":[68],"interactive":[70],"dashboards.":[71],"Results":[72],"confirm":[73],"that":[74],"input":[76],"affects":[77],"scores":[79],"can":[81],"lead":[82],"misleading":[84],"conclusions.":[85],"study":[87],"outlines":[88],"structured":[90],"process":[91],"profiling":[93],"cleaning":[95],"textual":[96],"data,":[97],"demonstrating":[98],"business":[100],"intelligence":[101],"tools":[102],"assist":[103],"monitoring":[105],"improving":[107],"quality.":[109],"proposed":[111],"applicable":[114],"practice":[116],"enhances":[118],"reliability":[120],"transparency":[122],"also":[127],"provides":[128],"foundation":[130],"future":[132],"advancements":[133],"preprocessing":[136],"within":[137],"natural":[138],"language":[139],"processing":[140],"tasks.":[141]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2025-10-10T00:00:00"}