{"id":"https://openalex.org/W2583616515","doi":"https://doi.org/10.1109/bigdata.2016.7841015","title":"The technical hashtag in Twitter data: A hadoop experience","display_name":"The technical hashtag in Twitter data: A hadoop experience","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583616515","doi":"https://doi.org/10.1109/bigdata.2016.7841015","mag":"2583616515"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","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/A5009385035","display_name":"Izabela Moise","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Izabela Moise","raw_affiliation_strings":["ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009385035"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.19608559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2016","issue":null,"first_page":"3519","last_page":"3528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.851942241191864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202086091041565},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7662401795387268},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7361453771591187},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6588201522827148},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5679445862770081},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.53705894947052},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5248380303382874},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5243147611618042},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5063382387161255},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4636894762516022},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4432690441608429},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34530943632125854},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23399770259857178},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18338072299957275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1665644347667694},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09455716609954834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08566191792488098}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.851942241191864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202086091041565},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7662401795387268},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7361453771591187},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6588201522827148},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5679445862770081},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.53705894947052},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5248380303382874},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5243147611618042},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5063382387161255},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4636894762516022},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4432690441608429},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34530943632125854},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23399770259857178},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18338072299957275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1665644347667694},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09455716609954834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08566191792488098},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2016.7841015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"mag:2787293939","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702282108343892","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1527789501","https://openalex.org/W1581485226","https://openalex.org/W1743243001","https://openalex.org/W1880262756","https://openalex.org/W1976323204","https://openalex.org/W2022783018","https://openalex.org/W2059314918","https://openalex.org/W2081212507","https://openalex.org/W2109734180","https://openalex.org/W2119738171","https://openalex.org/W2124499489","https://openalex.org/W2130428211","https://openalex.org/W2141631351","https://openalex.org/W2166354010","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W6631607175","https://openalex.org/W6634901647","https://openalex.org/W6637805623","https://openalex.org/W6639619044","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2799508461","https://openalex.org/W3191926225"],"abstract_inverted_index":{"The":[0],"continuously":[1],"growing":[2],"wealth":[3],"of":[4,26,50,70,89,128,131,157],"data":[5,10,159],"has":[6],"radically":[7],"changed":[8],"the":[9,14,48,51,68,86,90,126,141,149,154,161],"science":[11],"landscape.":[12],"At":[13],"same":[15],"time,":[16],"Big":[17,63],"Data":[18,64],"tools":[19],"have":[20],"known":[21],"important":[22,136],"progress":[23],"in":[24],"terms":[25],"optimising":[27],"performance":[28],"and":[29,78,92,104,160],"scalability.":[30],"However,":[31],"applying":[32],"them":[33],"into":[34],"practical":[35],"deployment":[36],"settings":[37],"is":[38,44],"still":[39],"a":[40,62,107,114],"challenging":[41],"task":[42],"that":[43,84],"highly":[45],"dependent":[46],"on":[47],"particularities":[49],"data.":[52,75],"In":[53],"this":[54],"paper,":[55],"we":[56],"present":[57],"our":[58,122,165],"experiences":[59],"with":[60,67,125],"implementing":[61],"analytics":[65],"pipeline":[66,97],"purpose":[69],"extracting":[71],"value":[72],"from":[73,102,153,164],"Twitter":[74,123,158],"We":[76,119,144],"acquire":[77],"process":[79],"nearly":[80],"60":[81],"million":[82],"tweets":[83,103],"capture":[85],"recent":[87],"outbreaks":[88],"Ebola":[91],"Zika":[93],"viruses.":[94],"Our":[95],"processing":[96],"first":[98],"extracts":[99],"useful":[100],"information":[101],"then":[105],"applies":[106],"topic":[108],"modelling":[109],"technique,":[110],"provided":[111],"by":[112],"Mahout,":[113],"Hadoop-based":[115],"machine":[116],"learning":[117],"library.":[118],"further":[120],"extend":[121],"analysis":[124],"study":[127],"temporal":[129],"evolution":[130],"daily":[132],"sentiment":[133],"toward":[134],"an":[135],"topic,":[137],"as":[138],"expressed":[139],"through":[140],"social":[142],"platform.":[143],"highlight":[145],"at":[146],"each":[147],"level,":[148],"technical":[150],"challenges":[151],"originating":[152],"specific":[155],"nature":[156],"lessons":[162],"drawn":[163],"work.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}