Stance and influence of Twitter users regarding the Brexit referendum View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2017-07-24

AUTHORS

Miha Grčar, Darko Cherepnalkoski, Igor Mozetič, Petra Kralj Novak

ABSTRACT

Social media are an important source of information about the political issues, reflecting, as well as influencing, public mood. We present an analysis of Twitter data, collected over 6 weeks before the Brexit referendum, held in the UK in June 2016. We address two questions: what is the relation between the Twitter mood and the referendum outcome, and who were the most influential Twitter users in the pro- and contra-Brexit camps? First, we construct a stance classification model by machine learning methods, and are then able to predict the stance of about one million UK-based Twitter users. The demography of Twitter users is, however, very different from the demography of the voters. By applying a simple age-adjusted mapping to the overall Twitter stance, the results show the prevalence of the pro-Brexit voters, something unexpected by most of the opinion polls. Second, we apply the Hirsch index to estimate the influence, and rank the Twitter users from both camps. We find that the most productive Twitter users are not the most influential, that the pro-Brexit camp was four times more influential, and had considerably larger impact on the campaign than the opponents. Third, we find that the top pro-Brexit communities are considerably more polarized than the contra-Brexit camp. These results show that social media provide a rich resource of data to be exploited, but accumulated knowledge and lessons learned from the opinion polls have to be adapted to the new data sources. More... »

PAGES

6

References to SciGraph publications

  • 2009. Evaluation Methods for Ordinal Classification in ADVANCES IN ARTIFICIAL INTELLIGENCE
  • 2001-08-30. A Simple Approach to Ordinal Classification in MACHINE LEARNING: ECML 2001
  • 1995. The Nature of Statistical Learning Theory in NONE
  • 2015-07-14. Sentiment leaning of influential communities in social networks in COMPUTATIONAL SOCIAL NETWORKS
  • 2016-06-01. Retweet networks of the European Parliament: evaluation of the community structure in APPLIED NETWORK SCIENCE
  • 2011-03-17. A Survey of Models and Algorithms for Social Influence Analysis in SOCIAL NETWORK DATA ANALYTICS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s40649-017-0042-6

    DOI

    http://dx.doi.org/10.1186/s40649-017-0042-6

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1090763390

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/29266132


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia", 
              "id": "http://www.grid.ac/institutes/grid.11375.31", 
              "name": [
                "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gr\u010dar", 
            "givenName": "Miha", 
            "id": "sg:person.014247505211.59", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014247505211.59"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia", 
              "id": "http://www.grid.ac/institutes/grid.11375.31", 
              "name": [
                "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cherepnalkoski", 
            "givenName": "Darko", 
            "id": "sg:person.012361326061.17", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012361326061.17"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia", 
              "id": "http://www.grid.ac/institutes/grid.11375.31", 
              "name": [
                "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mozeti\u010d", 
            "givenName": "Igor", 
            "id": "sg:person.01340706300.17", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01340706300.17"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia", 
              "id": "http://www.grid.ac/institutes/grid.11375.31", 
              "name": [
                "Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kralj Novak", 
            "givenName": "Petra", 
            "id": "sg:person.013746362424.05", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013746362424.05"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s41109-016-0001-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052700922", 
              "https://doi.org/10.1007/s41109-016-0001-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4757-2440-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027312764", 
              "https://doi.org/10.1007/978-1-4757-2440-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4419-8462-3_7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002348414", 
              "https://doi.org/10.1007/978-1-4419-8462-3_7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s40649-015-0016-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027060268", 
              "https://doi.org/10.1186/s40649-015-0016-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-01818-3_25", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041492799", 
              "https://doi.org/10.1007/978-3-642-01818-3_25"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-44795-4_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1016575098", 
              "https://doi.org/10.1007/3-540-44795-4_13"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-07-24", 
        "datePublishedReg": "2017-07-24", 
        "description": "Social media are an important source of information about the political issues, reflecting, as well as influencing, public mood. We present an analysis of Twitter data, collected over 6 weeks before the Brexit referendum, held in the UK in June 2016. We address two questions: what is the relation between the Twitter mood and the referendum outcome, and who were the most influential Twitter users in the pro- and contra-Brexit camps? First, we construct a stance classification model by machine learning methods, and are then able to predict the stance of about one million UK-based Twitter users. The demography of Twitter users is, however, very different from the demography of the voters. By applying a simple age-adjusted mapping to the overall Twitter stance, the results show the prevalence of the pro-Brexit voters, something unexpected by most of the opinion polls. Second, we apply the Hirsch index to estimate the influence, and rank the Twitter users from both camps. We find that the most productive Twitter users are not the most influential, that the pro-Brexit camp was four times more influential, and had considerably larger impact on the campaign than the opponents. Third, we find that the top pro-Brexit communities are considerably more polarized than the contra-Brexit camp. These results show that social media provide a rich resource of data to be exploited, but accumulated knowledge and lessons learned from the opinion polls have to be adapted to the new data sources.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s40649-017-0042-6", 
        "isAccessibleForFree": true, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.3938306", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1136872", 
            "issn": [
              "2197-4314"
            ], 
            "name": "Computational Social Networks", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "4"
          }
        ], 
        "keywords": [
          "Twitter users", 
          "opinion polls", 
          "Brexit referendum", 
          "machine learning methods", 
          "social media", 
          "new data sources", 
          "learning methods", 
          "influential Twitter users", 
          "classification model", 
          "Twitter data", 
          "political issues", 
          "users", 
          "public mood", 
          "referendum outcome", 
          "data sources", 
          "Twitter mood", 
          "voters", 
          "referendum", 
          "polls", 
          "stance", 
          "UK", 
          "demography", 
          "rich resource", 
          "cAMP", 
          "opponents", 
          "community", 
          "campaign", 
          "lessons", 
          "information", 
          "resources", 
          "issues", 
          "data", 
          "questions", 
          "relation", 
          "important source", 
          "mapping", 
          "knowledge", 
          "model", 
          "impact", 
          "method", 
          "results", 
          "influence", 
          "large impact", 
          "source", 
          "medium", 
          "time", 
          "outcomes", 
          "analysis", 
          "mood", 
          "Hirsch index", 
          "prevalence", 
          "index", 
          "weeks"
        ], 
        "name": "Stance and influence of Twitter users regarding the Brexit referendum", 
        "pagination": "6", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1090763390"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s40649-017-0042-6"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "29266132"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s40649-017-0042-6", 
          "https://app.dimensions.ai/details/publication/pub.1090763390"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-08-04T17:06", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/article/article_750.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s40649-017-0042-6"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s40649-017-0042-6'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s40649-017-0042-6'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s40649-017-0042-6'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s40649-017-0042-6'


     

    This table displays all metadata directly associated to this object as RDF triples.

    160 TRIPLES      21 PREDICATES      84 URIs      70 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s40649-017-0042-6 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N4e19822a60da4638a556ab62951e9646
    4 schema:citation sg:pub.10.1007/3-540-44795-4_13
    5 sg:pub.10.1007/978-1-4419-8462-3_7
    6 sg:pub.10.1007/978-1-4757-2440-0
    7 sg:pub.10.1007/978-3-642-01818-3_25
    8 sg:pub.10.1007/s41109-016-0001-4
    9 sg:pub.10.1186/s40649-015-0016-5
    10 schema:datePublished 2017-07-24
    11 schema:datePublishedReg 2017-07-24
    12 schema:description Social media are an important source of information about the political issues, reflecting, as well as influencing, public mood. We present an analysis of Twitter data, collected over 6 weeks before the Brexit referendum, held in the UK in June 2016. We address two questions: what is the relation between the Twitter mood and the referendum outcome, and who were the most influential Twitter users in the pro- and contra-Brexit camps? First, we construct a stance classification model by machine learning methods, and are then able to predict the stance of about one million UK-based Twitter users. The demography of Twitter users is, however, very different from the demography of the voters. By applying a simple age-adjusted mapping to the overall Twitter stance, the results show the prevalence of the pro-Brexit voters, something unexpected by most of the opinion polls. Second, we apply the Hirsch index to estimate the influence, and rank the Twitter users from both camps. We find that the most productive Twitter users are not the most influential, that the pro-Brexit camp was four times more influential, and had considerably larger impact on the campaign than the opponents. Third, we find that the top pro-Brexit communities are considerably more polarized than the contra-Brexit camp. These results show that social media provide a rich resource of data to be exploited, but accumulated knowledge and lessons learned from the opinion polls have to be adapted to the new data sources.
    13 schema:genre article
    14 schema:isAccessibleForFree true
    15 schema:isPartOf N3519130113a34b71ae1159f842659800
    16 N58ce4c2ee12149e7b770ab6b3fbecb8d
    17 sg:journal.1136872
    18 schema:keywords Brexit referendum
    19 Hirsch index
    20 Twitter data
    21 Twitter mood
    22 Twitter users
    23 UK
    24 analysis
    25 cAMP
    26 campaign
    27 classification model
    28 community
    29 data
    30 data sources
    31 demography
    32 impact
    33 important source
    34 index
    35 influence
    36 influential Twitter users
    37 information
    38 issues
    39 knowledge
    40 large impact
    41 learning methods
    42 lessons
    43 machine learning methods
    44 mapping
    45 medium
    46 method
    47 model
    48 mood
    49 new data sources
    50 opinion polls
    51 opponents
    52 outcomes
    53 political issues
    54 polls
    55 prevalence
    56 public mood
    57 questions
    58 referendum
    59 referendum outcome
    60 relation
    61 resources
    62 results
    63 rich resource
    64 social media
    65 source
    66 stance
    67 time
    68 users
    69 voters
    70 weeks
    71 schema:name Stance and influence of Twitter users regarding the Brexit referendum
    72 schema:pagination 6
    73 schema:productId N36f05d13b8d0483aad217160338a658b
    74 N6d0d9b261e14440d9dd0cedbe242f45b
    75 Nf06cdc72b7cf4cf8b64f84712ad9148a
    76 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090763390
    77 https://doi.org/10.1186/s40649-017-0042-6
    78 schema:sdDatePublished 2022-08-04T17:06
    79 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    80 schema:sdPublisher Nf378a6b9714e4b1590ae9d034b49cfa6
    81 schema:url https://doi.org/10.1186/s40649-017-0042-6
    82 sgo:license sg:explorer/license/
    83 sgo:sdDataset articles
    84 rdf:type schema:ScholarlyArticle
    85 N3519130113a34b71ae1159f842659800 schema:issueNumber 1
    86 rdf:type schema:PublicationIssue
    87 N36f05d13b8d0483aad217160338a658b schema:name doi
    88 schema:value 10.1186/s40649-017-0042-6
    89 rdf:type schema:PropertyValue
    90 N4089e2f19574463f8509e6a44ef6b7b1 rdf:first sg:person.013746362424.05
    91 rdf:rest rdf:nil
    92 N4e19822a60da4638a556ab62951e9646 rdf:first sg:person.014247505211.59
    93 rdf:rest Nf6f6b9348b49499f9543188634239921
    94 N58ce4c2ee12149e7b770ab6b3fbecb8d schema:volumeNumber 4
    95 rdf:type schema:PublicationVolume
    96 N6d0d9b261e14440d9dd0cedbe242f45b schema:name pubmed_id
    97 schema:value 29266132
    98 rdf:type schema:PropertyValue
    99 Naae58732fd6e4bad81dc4f69196d7280 rdf:first sg:person.01340706300.17
    100 rdf:rest N4089e2f19574463f8509e6a44ef6b7b1
    101 Nf06cdc72b7cf4cf8b64f84712ad9148a schema:name dimensions_id
    102 schema:value pub.1090763390
    103 rdf:type schema:PropertyValue
    104 Nf378a6b9714e4b1590ae9d034b49cfa6 schema:name Springer Nature - SN SciGraph project
    105 rdf:type schema:Organization
    106 Nf6f6b9348b49499f9543188634239921 rdf:first sg:person.012361326061.17
    107 rdf:rest Naae58732fd6e4bad81dc4f69196d7280
    108 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    109 schema:name Information and Computing Sciences
    110 rdf:type schema:DefinedTerm
    111 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    112 schema:name Artificial Intelligence and Image Processing
    113 rdf:type schema:DefinedTerm
    114 sg:grant.3938306 http://pending.schema.org/fundedItem sg:pub.10.1186/s40649-017-0042-6
    115 rdf:type schema:MonetaryGrant
    116 sg:journal.1136872 schema:issn 2197-4314
    117 schema:name Computational Social Networks
    118 schema:publisher Springer Nature
    119 rdf:type schema:Periodical
    120 sg:person.012361326061.17 schema:affiliation grid-institutes:grid.11375.31
    121 schema:familyName Cherepnalkoski
    122 schema:givenName Darko
    123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012361326061.17
    124 rdf:type schema:Person
    125 sg:person.01340706300.17 schema:affiliation grid-institutes:grid.11375.31
    126 schema:familyName Mozetič
    127 schema:givenName Igor
    128 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01340706300.17
    129 rdf:type schema:Person
    130 sg:person.013746362424.05 schema:affiliation grid-institutes:grid.11375.31
    131 schema:familyName Kralj Novak
    132 schema:givenName Petra
    133 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013746362424.05
    134 rdf:type schema:Person
    135 sg:person.014247505211.59 schema:affiliation grid-institutes:grid.11375.31
    136 schema:familyName Grčar
    137 schema:givenName Miha
    138 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014247505211.59
    139 rdf:type schema:Person
    140 sg:pub.10.1007/3-540-44795-4_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016575098
    141 https://doi.org/10.1007/3-540-44795-4_13
    142 rdf:type schema:CreativeWork
    143 sg:pub.10.1007/978-1-4419-8462-3_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002348414
    144 https://doi.org/10.1007/978-1-4419-8462-3_7
    145 rdf:type schema:CreativeWork
    146 sg:pub.10.1007/978-1-4757-2440-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027312764
    147 https://doi.org/10.1007/978-1-4757-2440-0
    148 rdf:type schema:CreativeWork
    149 sg:pub.10.1007/978-3-642-01818-3_25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041492799
    150 https://doi.org/10.1007/978-3-642-01818-3_25
    151 rdf:type schema:CreativeWork
    152 sg:pub.10.1007/s41109-016-0001-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052700922
    153 https://doi.org/10.1007/s41109-016-0001-4
    154 rdf:type schema:CreativeWork
    155 sg:pub.10.1186/s40649-015-0016-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027060268
    156 https://doi.org/10.1186/s40649-015-0016-5
    157 rdf:type schema:CreativeWork
    158 grid-institutes:grid.11375.31 schema:alternateName Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia
    159 schema:name Department of Knowledge Technologies, Jozef Stefan Institute, Jamova 39, 1000, Ljubljana, Slovenia
    160 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...