Measuring and Explaining Political Sophistication through Textual Complexity

Kenneth Benoit, Kevin Munger, Arthur Spirling

    Research output: Contribution to journalArticle

    Abstract

    Political scientists lack domain-specific measures for the purpose of measuring the sophistication of political communication. We systematically review the shortcomings of existing approaches, before developing a new and better method along with software tools to apply it. We use crowdsourcing to perform thousands of pairwise comparisons of text snippets and incorporate these results into a statistical model of sophistication. This includes previously excluded features such as parts of speech and a measure of word rarity derived from dynamic term frequencies in the Google Books data set. Our technique not only shows which features are appropriate to the political domain and how, but also provides a measure easily applied and rescaled to political texts in a way that facilitates probabilistic comparisons. We reanalyze the State of the Union corpus to demonstrate how conclusions differ when using our improved approach, including the ability to compare complexity as a function of covariates.

    Original languageEnglish (US)
    Pages (from-to)491-508
    Number of pages18
    JournalAmerican Journal of Political Science
    Volume63
    Issue number2
    DOIs
    StatePublished - Apr 1 2019

    Fingerprint

    political communication
    political scientist
    search engine
    lack
    ability
    software

    ASJC Scopus subject areas

    • Sociology and Political Science
    • Political Science and International Relations

    Cite this

    Measuring and Explaining Political Sophistication through Textual Complexity. / Benoit, Kenneth; Munger, Kevin; Spirling, Arthur.

    In: American Journal of Political Science, Vol. 63, No. 2, 01.04.2019, p. 491-508.

    Research output: Contribution to journalArticle

    Benoit, Kenneth ; Munger, Kevin ; Spirling, Arthur. / Measuring and Explaining Political Sophistication through Textual Complexity. In: American Journal of Political Science. 2019 ; Vol. 63, No. 2. pp. 491-508.
    @article{f96fcd4755ae4100a31129f1ab84d57f,
    title = "Measuring and Explaining Political Sophistication through Textual Complexity",
    abstract = "Political scientists lack domain-specific measures for the purpose of measuring the sophistication of political communication. We systematically review the shortcomings of existing approaches, before developing a new and better method along with software tools to apply it. We use crowdsourcing to perform thousands of pairwise comparisons of text snippets and incorporate these results into a statistical model of sophistication. This includes previously excluded features such as parts of speech and a measure of word rarity derived from dynamic term frequencies in the Google Books data set. Our technique not only shows which features are appropriate to the political domain and how, but also provides a measure easily applied and rescaled to political texts in a way that facilitates probabilistic comparisons. We reanalyze the State of the Union corpus to demonstrate how conclusions differ when using our improved approach, including the ability to compare complexity as a function of covariates.",
    author = "Kenneth Benoit and Kevin Munger and Arthur Spirling",
    year = "2019",
    month = "4",
    day = "1",
    doi = "10.1111/ajps.12423",
    language = "English (US)",
    volume = "63",
    pages = "491--508",
    journal = "American Journal of Political Science",
    issn = "0092-5853",
    publisher = "Wiley-Blackwell",
    number = "2",

    }

    TY - JOUR

    T1 - Measuring and Explaining Political Sophistication through Textual Complexity

    AU - Benoit, Kenneth

    AU - Munger, Kevin

    AU - Spirling, Arthur

    PY - 2019/4/1

    Y1 - 2019/4/1

    N2 - Political scientists lack domain-specific measures for the purpose of measuring the sophistication of political communication. We systematically review the shortcomings of existing approaches, before developing a new and better method along with software tools to apply it. We use crowdsourcing to perform thousands of pairwise comparisons of text snippets and incorporate these results into a statistical model of sophistication. This includes previously excluded features such as parts of speech and a measure of word rarity derived from dynamic term frequencies in the Google Books data set. Our technique not only shows which features are appropriate to the political domain and how, but also provides a measure easily applied and rescaled to political texts in a way that facilitates probabilistic comparisons. We reanalyze the State of the Union corpus to demonstrate how conclusions differ when using our improved approach, including the ability to compare complexity as a function of covariates.

    AB - Political scientists lack domain-specific measures for the purpose of measuring the sophistication of political communication. We systematically review the shortcomings of existing approaches, before developing a new and better method along with software tools to apply it. We use crowdsourcing to perform thousands of pairwise comparisons of text snippets and incorporate these results into a statistical model of sophistication. This includes previously excluded features such as parts of speech and a measure of word rarity derived from dynamic term frequencies in the Google Books data set. Our technique not only shows which features are appropriate to the political domain and how, but also provides a measure easily applied and rescaled to political texts in a way that facilitates probabilistic comparisons. We reanalyze the State of the Union corpus to demonstrate how conclusions differ when using our improved approach, including the ability to compare complexity as a function of covariates.

    UR - http://www.scopus.com/inward/record.url?scp=85064837106&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85064837106&partnerID=8YFLogxK

    U2 - 10.1111/ajps.12423

    DO - 10.1111/ajps.12423

    M3 - Article

    AN - SCOPUS:85064837106

    VL - 63

    SP - 491

    EP - 508

    JO - American Journal of Political Science

    JF - American Journal of Political Science

    SN - 0092-5853

    IS - 2

    ER -