Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls
This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92,441 tweets r...
Gespeichert in:
| Veröffentlicht in: | Journal of information technology & politics 2017-01, Vol.14 (1), p.34-45 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 45 |
|---|---|
| container_issue | 1 |
| container_start_page | 34 |
| container_title | Journal of information technology & politics |
| container_volume | 14 |
| creator | Oliveira, Daniel José Silva Bermejo, Paulo Henrique de Souza dos Santos, Pâmela Aparecida |
| description | This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92,441 tweets related to the Brazilian presidential candidates during the second round of elections in 2014. The analysis results were compared with six voter preference polls conducted by the Datafolha Research Institute. The results showed that sentiment analysis may indicate voter preferences at an accuracy that was only 1% to 8% different than that of traditional research, which has an average accuracy of 81.05%. |
| doi_str_mv | 10.1080/19331681.2016.1214094 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_infor</sourceid><recordid>TN_cdi_proquest_journals_1920418492</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1920418492</sourcerecordid><originalsourceid>FETCH-LOGICAL-c338t-b5070299e2a7cc2e07e4880510717ee1db288fdb6c8455999afe165c3706565b3</originalsourceid><addsrcrecordid>eNp9UE1LxDAQLaLguvoThIDnrpm0aZOTLotfIHhR8BbSdIpZ2qYm8WP_vVl29ehl5s3jzWPmZdk50AVQQS9BFgVUAhaMQrUABiWV5UE22_I5VPL18A8LOM5OQlhTyqtasln2vdIjCc5Y3ZMBW6uJx09MQ3xDMnns0ONoMBDXkU8X0YcrsiTGDZP2NriRNBi_EJMHjtEOqRA96n4TbEigJdHr1kbrEkfcZMeEyOT6PpxmR53uA57t-zx7ub15Xt3nj093D6vlY26KQsS84bSmTEpkujaGIa2xFIJyoDXUiNA2TIiubSojSs6llLpDqLgpalrxijfFPLvY-U7evX9giGrtPnw6JyiQjJYgSsmSiu9UxrsQ0ttq8nbQfqOAqm3I6jdktQ1Z7UNOe9e7PTt2zg_6y_m-VVFveuc7r0djgyr-t_gBZP2Ejw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1920418492</pqid></control><display><type>article</type><title>Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls</title><source>EBSCOhost Political Science Complete</source><source>Worldwide Political Science Abstracts</source><creator>Oliveira, Daniel José Silva ; Bermejo, Paulo Henrique de Souza ; dos Santos, Pâmela Aparecida</creator><creatorcontrib>Oliveira, Daniel José Silva ; Bermejo, Paulo Henrique de Souza ; dos Santos, Pâmela Aparecida</creatorcontrib><description>This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92,441 tweets related to the Brazilian presidential candidates during the second round of elections in 2014. The analysis results were compared with six voter preference polls conducted by the Datafolha Research Institute. The results showed that sentiment analysis may indicate voter preferences at an accuracy that was only 1% to 8% different than that of traditional research, which has an average accuracy of 81.05%.</description><identifier>ISSN: 1933-1681</identifier><identifier>EISSN: 1933-169X</identifier><identifier>DOI: 10.1080/19331681.2016.1214094</identifier><language>eng</language><publisher>Abingdon: Routledge</publisher><subject>Accuracy ; Candidates ; Citizens ; Data mining ; Digital media ; Election results ; Elections ; Mass media ; opinion mining ; opinion polls ; Political campaigns ; Polls & surveys ; Presidential candidates ; Presidential elections ; Public opinion ; Public opinion surveys ; Sentiment analysis ; Social media ; Social networks ; Twitter ; Voter behavior ; Voters</subject><ispartof>Journal of information technology & politics, 2017-01, Vol.14 (1), p.34-45</ispartof><rights>2017 Taylor & Francis 2017</rights><rights>2017 Taylor & Francis</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c338t-b5070299e2a7cc2e07e4880510717ee1db288fdb6c8455999afe165c3706565b3</citedby><cites>FETCH-LOGICAL-c338t-b5070299e2a7cc2e07e4880510717ee1db288fdb6c8455999afe165c3706565b3</cites><orcidid>0000-0002-0475-6564</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Oliveira, Daniel José Silva</creatorcontrib><creatorcontrib>Bermejo, Paulo Henrique de Souza</creatorcontrib><creatorcontrib>dos Santos, Pâmela Aparecida</creatorcontrib><title>Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls</title><title>Journal of information technology & politics</title><description>This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92,441 tweets related to the Brazilian presidential candidates during the second round of elections in 2014. The analysis results were compared with six voter preference polls conducted by the Datafolha Research Institute. The results showed that sentiment analysis may indicate voter preferences at an accuracy that was only 1% to 8% different than that of traditional research, which has an average accuracy of 81.05%.</description><subject>Accuracy</subject><subject>Candidates</subject><subject>Citizens</subject><subject>Data mining</subject><subject>Digital media</subject><subject>Election results</subject><subject>Elections</subject><subject>Mass media</subject><subject>opinion mining</subject><subject>opinion polls</subject><subject>Political campaigns</subject><subject>Polls & surveys</subject><subject>Presidential candidates</subject><subject>Presidential elections</subject><subject>Public opinion</subject><subject>Public opinion surveys</subject><subject>Sentiment analysis</subject><subject>Social media</subject><subject>Social networks</subject><subject>Twitter</subject><subject>Voter behavior</subject><subject>Voters</subject><issn>1933-1681</issn><issn>1933-169X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>7UB</sourceid><recordid>eNp9UE1LxDAQLaLguvoThIDnrpm0aZOTLotfIHhR8BbSdIpZ2qYm8WP_vVl29ehl5s3jzWPmZdk50AVQQS9BFgVUAhaMQrUABiWV5UE22_I5VPL18A8LOM5OQlhTyqtasln2vdIjCc5Y3ZMBW6uJx09MQ3xDMnns0ONoMBDXkU8X0YcrsiTGDZP2NriRNBi_EJMHjtEOqRA96n4TbEigJdHr1kbrEkfcZMeEyOT6PpxmR53uA57t-zx7ub15Xt3nj093D6vlY26KQsS84bSmTEpkujaGIa2xFIJyoDXUiNA2TIiubSojSs6llLpDqLgpalrxijfFPLvY-U7evX9giGrtPnw6JyiQjJYgSsmSiu9UxrsQ0ttq8nbQfqOAqm3I6jdktQ1Z7UNOe9e7PTt2zg_6y_m-VVFveuc7r0djgyr-t_gBZP2Ejw</recordid><startdate>20170102</startdate><enddate>20170102</enddate><creator>Oliveira, Daniel José Silva</creator><creator>Bermejo, Paulo Henrique de Souza</creator><creator>dos Santos, Pâmela Aparecida</creator><general>Routledge</general><general>Taylor & Francis Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TA</scope><scope>7UB</scope><scope>8BJ</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>FQK</scope><scope>JBE</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-0475-6564</orcidid></search><sort><creationdate>20170102</creationdate><title>Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls</title><author>Oliveira, Daniel José Silva ; Bermejo, Paulo Henrique de Souza ; dos Santos, Pâmela Aparecida</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c338t-b5070299e2a7cc2e07e4880510717ee1db288fdb6c8455999afe165c3706565b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Accuracy</topic><topic>Candidates</topic><topic>Citizens</topic><topic>Data mining</topic><topic>Digital media</topic><topic>Election results</topic><topic>Elections</topic><topic>Mass media</topic><topic>opinion mining</topic><topic>opinion polls</topic><topic>Political campaigns</topic><topic>Polls & surveys</topic><topic>Presidential candidates</topic><topic>Presidential elections</topic><topic>Public opinion</topic><topic>Public opinion surveys</topic><topic>Sentiment analysis</topic><topic>Social media</topic><topic>Social networks</topic><topic>Twitter</topic><topic>Voter behavior</topic><topic>Voters</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Oliveira, Daniel José Silva</creatorcontrib><creatorcontrib>Bermejo, Paulo Henrique de Souza</creatorcontrib><creatorcontrib>dos Santos, Pâmela Aparecida</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Materials Business File</collection><collection>Worldwide Political Science Abstracts</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>Technology Research Database</collection><collection>Library & Information Sciences Abstracts (LISA)</collection><collection>Library & Information Science Abstracts (LISA)</collection><collection>International Bibliography of the Social Sciences</collection><collection>International Bibliography of the Social Sciences</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Journal of information technology & politics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Oliveira, Daniel José Silva</au><au>Bermejo, Paulo Henrique de Souza</au><au>dos Santos, Pâmela Aparecida</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls</atitle><jtitle>Journal of information technology & politics</jtitle><date>2017-01-02</date><risdate>2017</risdate><volume>14</volume><issue>1</issue><spage>34</spage><epage>45</epage><pages>34-45</pages><issn>1933-1681</issn><eissn>1933-169X</eissn><abstract>This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92,441 tweets related to the Brazilian presidential candidates during the second round of elections in 2014. The analysis results were compared with six voter preference polls conducted by the Datafolha Research Institute. The results showed that sentiment analysis may indicate voter preferences at an accuracy that was only 1% to 8% different than that of traditional research, which has an average accuracy of 81.05%.</abstract><cop>Abingdon</cop><pub>Routledge</pub><doi>10.1080/19331681.2016.1214094</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-0475-6564</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1933-1681 |
| ispartof | Journal of information technology & politics, 2017-01, Vol.14 (1), p.34-45 |
| issn | 1933-1681 1933-169X |
| language | eng |
| recordid | cdi_proquest_journals_1920418492 |
| source | EBSCOhost Political Science Complete; Worldwide Political Science Abstracts |
| subjects | Accuracy Candidates Citizens Data mining Digital media Election results Elections Mass media opinion mining opinion polls Political campaigns Polls & surveys Presidential candidates Presidential elections Public opinion Public opinion surveys Sentiment analysis Social media Social networks Voter behavior Voters |
| title | Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T04%3A57%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_infor&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Can%20social%20media%20reveal%20the%20preferences%20of%20voters?%20A%20comparison%20between%20sentiment%20analysis%20and%20traditional%20opinion%20polls&rft.jtitle=Journal%20of%20information%20technology%20&%20politics&rft.au=Oliveira,%20Daniel%20Jos%C3%A9%20Silva&rft.date=2017-01-02&rft.volume=14&rft.issue=1&rft.spage=34&rft.epage=45&rft.pages=34-45&rft.issn=1933-1681&rft.eissn=1933-169X&rft_id=info:doi/10.1080/19331681.2016.1214094&rft_dat=%3Cproquest_infor%3E1920418492%3C/proquest_infor%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1920418492&rft_id=info:pmid/&rfr_iscdi=true |