Psephological Investigations: Tweets, Votes, and Unknown Unknowns in the Republican Nomination Process

Michael JENSEN, Nick Anstead

    Research output: Contribution to journalArticle

    20 Citations (Scopus)

    Abstract

    This paper analyzes the utility of using information contained within Twitter posts in predicting electoral outcomes. Particularly, we are interested in patterns in Twitter communications that can help explain differences between published opinion polls and the actual vote. We consider three categories of models. The first is a mentions model that examines the correspondence between the prevalence of communications about a candidate and electoral outcomes. The second series of models treat Twitter similar to a prediction market, aggregating not candidate preferences but predictions of the electoral result. Last, we consider whether the rediffusion of tweets about a candidate is a reliable predictor of the candidate's performance. The results find inconsistent support for the predictive value of Twitter mentions as an estimate of the overall vote, but these communications provide some evidence of otherwise undetected shifts in momentum with respect to the aggregated predictions of candidate performance and message rediffusion via retweets containing information about a particular candidate. Given the nature of the information extractable, these data are most sensitive to detecting changes in momentum
    Original languageEnglish
    Pages (from-to)161-182
    Number of pages22
    JournalPolicy and Internet
    Volume5
    Issue number2
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    voter
    candidacy
    twitter
    Broadcasting
    Communication
    Momentum
    communications
    opinion poll
    performance
    market
    evidence

    Cite this

    @article{cb95cf5315f9466d8a1cdaebbde5ddc6,
    title = "Psephological Investigations: Tweets, Votes, and Unknown Unknowns in the Republican Nomination Process",
    abstract = "This paper analyzes the utility of using information contained within Twitter posts in predicting electoral outcomes. Particularly, we are interested in patterns in Twitter communications that can help explain differences between published opinion polls and the actual vote. We consider three categories of models. The first is a mentions model that examines the correspondence between the prevalence of communications about a candidate and electoral outcomes. The second series of models treat Twitter similar to a prediction market, aggregating not candidate preferences but predictions of the electoral result. Last, we consider whether the rediffusion of tweets about a candidate is a reliable predictor of the candidate's performance. The results find inconsistent support for the predictive value of Twitter mentions as an estimate of the overall vote, but these communications provide some evidence of otherwise undetected shifts in momentum with respect to the aggregated predictions of candidate performance and message rediffusion via retweets containing information about a particular candidate. Given the nature of the information extractable, these data are most sensitive to detecting changes in momentum",
    author = "Michael JENSEN and Nick Anstead",
    year = "2013",
    doi = "10.1002/1944-2866.POI329",
    language = "English",
    volume = "5",
    pages = "161--182",
    journal = "Policy and Internet",
    issn = "1944-2866",
    publisher = "John Wiley & Sons",
    number = "2",

    }

    Psephological Investigations: Tweets, Votes, and Unknown Unknowns in the Republican Nomination Process. / JENSEN, Michael; Anstead, Nick.

    In: Policy and Internet, Vol. 5, No. 2, 2013, p. 161-182.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Psephological Investigations: Tweets, Votes, and Unknown Unknowns in the Republican Nomination Process

    AU - JENSEN, Michael

    AU - Anstead, Nick

    PY - 2013

    Y1 - 2013

    N2 - This paper analyzes the utility of using information contained within Twitter posts in predicting electoral outcomes. Particularly, we are interested in patterns in Twitter communications that can help explain differences between published opinion polls and the actual vote. We consider three categories of models. The first is a mentions model that examines the correspondence between the prevalence of communications about a candidate and electoral outcomes. The second series of models treat Twitter similar to a prediction market, aggregating not candidate preferences but predictions of the electoral result. Last, we consider whether the rediffusion of tweets about a candidate is a reliable predictor of the candidate's performance. The results find inconsistent support for the predictive value of Twitter mentions as an estimate of the overall vote, but these communications provide some evidence of otherwise undetected shifts in momentum with respect to the aggregated predictions of candidate performance and message rediffusion via retweets containing information about a particular candidate. Given the nature of the information extractable, these data are most sensitive to detecting changes in momentum

    AB - This paper analyzes the utility of using information contained within Twitter posts in predicting electoral outcomes. Particularly, we are interested in patterns in Twitter communications that can help explain differences between published opinion polls and the actual vote. We consider three categories of models. The first is a mentions model that examines the correspondence between the prevalence of communications about a candidate and electoral outcomes. The second series of models treat Twitter similar to a prediction market, aggregating not candidate preferences but predictions of the electoral result. Last, we consider whether the rediffusion of tweets about a candidate is a reliable predictor of the candidate's performance. The results find inconsistent support for the predictive value of Twitter mentions as an estimate of the overall vote, but these communications provide some evidence of otherwise undetected shifts in momentum with respect to the aggregated predictions of candidate performance and message rediffusion via retweets containing information about a particular candidate. Given the nature of the information extractable, these data are most sensitive to detecting changes in momentum

    U2 - 10.1002/1944-2866.POI329

    DO - 10.1002/1944-2866.POI329

    M3 - Article

    VL - 5

    SP - 161

    EP - 182

    JO - Policy and Internet

    JF - Policy and Internet

    SN - 1944-2866

    IS - 2

    ER -