{"id":"https://openalex.org/W4391547654","doi":"https://doi.org/10.1109/tbdata.2024.3362193","title":"ALTRUIST: A Python Package to Emulate a Virtual Digital Cohort Study Using Social Media Data","display_name":"ALTRUIST: A Python Package to Emulate a Virtual Digital Cohort Study Using Social Media Data","publication_year":2024,"publication_date":"2024-02-05","ids":{"openalex":"https://openalex.org/W4391547654","doi":"https://doi.org/10.1109/tbdata.2024.3362193"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2024.3362193","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tbdata.2024.3362193","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/10420428.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"type":"software-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/10420428.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014312610","display_name":"Charline Bour","orcid":"https://orcid.org/0000-0001-8537-2097"},"institutions":[{"id":"https://openalex.org/I4210101141","display_name":"Luxembourg Institute of Health","ror":"https://ror.org/012m8gv78","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210101141"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Charline Bour","raw_affiliation_strings":["Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-8537-2097","affiliations":[{"raw_affiliation_string":"Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]},{"raw_affiliation_string":"Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044547931","display_name":"Abir Elb\u00e9ji","orcid":"https://orcid.org/0000-0002-5293-4337"},"institutions":[{"id":"https://openalex.org/I4210101141","display_name":"Luxembourg Institute of Health","ror":"https://ror.org/012m8gv78","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210101141"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Abir Elbeji","raw_affiliation_strings":["Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-5293-4337","affiliations":[{"raw_affiliation_string":"Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]},{"raw_affiliation_string":"Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087930272","display_name":"Luigi De Giovanni","orcid":"https://orcid.org/0000-0002-8035-0013"},"institutions":[{"id":"https://openalex.org/I4210101141","display_name":"Luxembourg Institute of Health","ror":"https://ror.org/012m8gv78","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210101141"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Luigi De Giovanni","raw_affiliation_strings":["Data Integration and Analysis Unit, Luxembourg Institute of Health, Strassen, Luxembourg","Data Integration and Analysis Unit, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg"],"raw_orcid":"https://orcid.org/0009-0007-3985-7190","affiliations":[{"raw_affiliation_string":"Data Integration and Analysis Unit, Luxembourg Institute of Health, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]},{"raw_affiliation_string":"Data Integration and Analysis Unit, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006626842","display_name":"Adrian Ahne","orcid":"https://orcid.org/0000-0001-9463-9064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian Ahne","raw_affiliation_strings":["Akuity Care, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-9463-9064","affiliations":[{"raw_affiliation_string":"Akuity Care, Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064275163","display_name":"Guy Fagherazzi","orcid":"https://orcid.org/0000-0001-5033-5966"},"institutions":[{"id":"https://openalex.org/I4210101141","display_name":"Luxembourg Institute of Health","ror":"https://ror.org/012m8gv78","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210101141"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Guy Fagherazzi","raw_affiliation_strings":["Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg","Director of the Department of Precision Health and a Group Leader, Luxembourg Institute of Health, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-5033-5966","affiliations":[{"raw_affiliation_string":"Department of Precision Health, Deep Digital Phenotyping Research Unit, Luxembourg Institute of Health, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]},{"raw_affiliation_string":"Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, Strassen, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]},{"raw_affiliation_string":"Director of the Department of Precision Health and a Group Leader, Luxembourg Institute of Health, Luxembourg","institution_ids":["https://openalex.org/I4210101141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"4","first_page":"568","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9404000043869019,"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":0.6681098937988281},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6667322516441345},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.612993597984314},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.5292683839797974},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4390362501144409},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4254714250564575},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.41267579793930054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.327400267124176},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.25212377309799194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17344292998313904},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1279590129852295},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.08297666907310486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07728952169418335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681098937988281},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6667322516441345},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.612993597984314},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.5292683839797974},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4390362501144409},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4254714250564575},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.41267579793930054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.327400267124176},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.25212377309799194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17344292998313904},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1279590129852295},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.08297666907310486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07728952169418335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2024.3362193","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tbdata.2024.3362193","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/10420428.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tbdata.2024.3362193","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tbdata.2024.3362193","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/10420428.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391547654.pdf","grobid_xml":"https://content.openalex.org/works/W4391547654.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1203882361","https://openalex.org/W1229914050","https://openalex.org/W1984732538","https://openalex.org/W2033465810","https://openalex.org/W2087598211","https://openalex.org/W2135800910","https://openalex.org/W2140910804","https://openalex.org/W2204187200","https://openalex.org/W2238346964","https://openalex.org/W2508402845","https://openalex.org/W2583712097","https://openalex.org/W2784537350","https://openalex.org/W2799393207","https://openalex.org/W2896457183","https://openalex.org/W2969754783","https://openalex.org/W2970641574","https://openalex.org/W2972749265","https://openalex.org/W2995624592","https://openalex.org/W3014785748","https://openalex.org/W3034120808","https://openalex.org/W3104186312","https://openalex.org/W3132350734","https://openalex.org/W3136092764","https://openalex.org/W3196334477","https://openalex.org/W4205170775","https://openalex.org/W4281399014","https://openalex.org/W4283724384","https://openalex.org/W4285170012","https://openalex.org/W4322493184","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W4401016539","https://openalex.org/W4400651710","https://openalex.org/W4406202791","https://openalex.org/W4405093211","https://openalex.org/W4403672447"],"abstract_inverted_index":{"Epidemiological":[0],"cohort":[1,91,99,133],"studies":[2,17,92,100],"play":[3],"a":[4,36,81,131,137],"crucial":[5],"role":[6],"in":[7],"identifying":[8],"risk":[9],"factors":[10],"for":[11,40,171],"various":[12,185],"outcomes":[13],"among":[14],"participants.":[15],"These":[16],"are":[18],"often":[19],"time-consuming":[20],"and":[21,26,43,126,155,178,194],"costly":[22],"due":[23],"to":[24,97,144,182],"recruitment":[25],"long-term":[27],"follow-up.":[28],"Social":[29],"media":[30],"(SM)":[31],"data":[32,79,123,183],"has":[33],"emerged":[34],"as":[35,46,80,94,167],"valuable":[37],"complementary":[38],"source":[39],"digital":[41,90],"epidemiology":[42],"health":[44,198],"research,":[45],"online":[47,186],"communities":[48,187],"of":[49,88,117,165,188],"patients":[50],"regularly":[51],"share":[52],"information":[53,66,157],"about":[54,67],"their":[55],"illnesses.":[56],"Unlike":[57],"traditional":[58,132,191],"clinical":[59],"questionnaires,":[60],"SM":[61,78,102,150],"offer":[62],"unstructured":[63],"but":[64],"insightful":[65],"patients\u2019":[68],"disease":[69],"burden.":[70],"Yet,":[71],"there":[72],"is":[73,176],"limited":[74],"guidance":[75],"on":[76,119,142,158],"analyzing":[77],"prospective":[82],"cohort.":[83],"We":[84,135],"presented":[85],"the":[86,146,163],"concept":[87],"virtual":[89],"(VDCS)":[93],"an":[95,110,168],"approach":[96],"replicate":[98],"using":[101],"data.":[103],"In":[104],"this":[105],"paper,":[106],"we":[107,161],"introduce":[108],"ALTRUIST,":[109],"open-source":[111],"Python":[112],"package":[113],"enabling":[114],"standardized":[115],"generation":[116],"VDCS":[118,166],"SM.":[120],"ALTRUIST":[121,175],"facilitates":[122],"collection,":[124],"preprocessing,":[125],"analysis":[127],"steps":[128],"that":[129],"mimic":[130],"study.":[134],"provide":[136],"practical":[138],"use":[139],"case":[140],"focusing":[141],"diabetes":[143],"illustrate":[145],"methodology.":[147],"By":[148],"leveraging":[149],"data,":[151],"which":[152],"offers":[153],"large-scale":[154],"cost-effective":[156],"users\u2019":[159],"health,":[160],"demonstrate":[162],"potential":[164],"essential":[169],"tool":[170],"specific":[172],"research":[173],"questions.":[174],"customizable":[177],"can":[179],"be":[180],"applied":[181],"from":[184],"patients,":[189],"complementing":[190],"epidemiological":[192],"methods":[193],"promoting":[195],"minimally":[196],"disruptive":[197],"research.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}