Scaling policy preferences from coded political texts

Lowe Will, Kenneth Benoit, Mikhaylov Slava, Michael Laver

    Research output: Contribution to journalArticle

    Abstract

    Scholars estimating policy positions from political texts typically code words or sentences and then build left-right policy scales based on the relative frequencies of text units coded into different categories. Here we reexamine such scales and propose a theoretically and linguistically superior alternative based on the logarithm of oddsratios. We contrast this scale with the current approach of the Comparative Manifesto Project (CMP), showing that our proposed logit scale avoids widely acknowledged flaws in previous approaches. We validate the new scale using independent expert surveys. Using existing CMP data, we show how to estimate more distinct policy dimensions, for more years, than has been possible before, and make this dataset publicly available. Finally, we draw some conclusions about the future design of coding schemes for political texts.

    Original languageEnglish (US)
    Pages (from-to)123-155
    Number of pages33
    JournalLegislative Studies Quarterly
    Volume36
    Issue number1
    DOIs
    StatePublished - Feb 2011

    Fingerprint

    scaling
    expert survey
    coding

    ASJC Scopus subject areas

    • Sociology and Political Science

    Cite this

    Scaling policy preferences from coded political texts. / Will, Lowe; Benoit, Kenneth; Slava, Mikhaylov; Laver, Michael.

    In: Legislative Studies Quarterly, Vol. 36, No. 1, 02.2011, p. 123-155.

    Research output: Contribution to journalArticle

    Will, Lowe ; Benoit, Kenneth ; Slava, Mikhaylov ; Laver, Michael. / Scaling policy preferences from coded political texts. In: Legislative Studies Quarterly. 2011 ; Vol. 36, No. 1. pp. 123-155.
    @article{e5828f4e91c8456ab2ef7898710e769b,
    title = "Scaling policy preferences from coded political texts",
    abstract = "Scholars estimating policy positions from political texts typically code words or sentences and then build left-right policy scales based on the relative frequencies of text units coded into different categories. Here we reexamine such scales and propose a theoretically and linguistically superior alternative based on the logarithm of oddsratios. We contrast this scale with the current approach of the Comparative Manifesto Project (CMP), showing that our proposed logit scale avoids widely acknowledged flaws in previous approaches. We validate the new scale using independent expert surveys. Using existing CMP data, we show how to estimate more distinct policy dimensions, for more years, than has been possible before, and make this dataset publicly available. Finally, we draw some conclusions about the future design of coding schemes for political texts.",
    author = "Lowe Will and Kenneth Benoit and Mikhaylov Slava and Michael Laver",
    year = "2011",
    month = "2",
    doi = "10.1111/j.1939-9162.2010.00006.x",
    language = "English (US)",
    volume = "36",
    pages = "123--155",
    journal = "Legislative Studies Quarterly",
    issn = "0362-9805",
    publisher = "Wiley-Blackwell",
    number = "1",

    }

    TY - JOUR

    T1 - Scaling policy preferences from coded political texts

    AU - Will, Lowe

    AU - Benoit, Kenneth

    AU - Slava, Mikhaylov

    AU - Laver, Michael

    PY - 2011/2

    Y1 - 2011/2

    N2 - Scholars estimating policy positions from political texts typically code words or sentences and then build left-right policy scales based on the relative frequencies of text units coded into different categories. Here we reexamine such scales and propose a theoretically and linguistically superior alternative based on the logarithm of oddsratios. We contrast this scale with the current approach of the Comparative Manifesto Project (CMP), showing that our proposed logit scale avoids widely acknowledged flaws in previous approaches. We validate the new scale using independent expert surveys. Using existing CMP data, we show how to estimate more distinct policy dimensions, for more years, than has been possible before, and make this dataset publicly available. Finally, we draw some conclusions about the future design of coding schemes for political texts.

    AB - Scholars estimating policy positions from political texts typically code words or sentences and then build left-right policy scales based on the relative frequencies of text units coded into different categories. Here we reexamine such scales and propose a theoretically and linguistically superior alternative based on the logarithm of oddsratios. We contrast this scale with the current approach of the Comparative Manifesto Project (CMP), showing that our proposed logit scale avoids widely acknowledged flaws in previous approaches. We validate the new scale using independent expert surveys. Using existing CMP data, we show how to estimate more distinct policy dimensions, for more years, than has been possible before, and make this dataset publicly available. Finally, we draw some conclusions about the future design of coding schemes for political texts.

    UR - http://www.scopus.com/inward/record.url?scp=79951694330&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79951694330&partnerID=8YFLogxK

    U2 - 10.1111/j.1939-9162.2010.00006.x

    DO - 10.1111/j.1939-9162.2010.00006.x

    M3 - Article

    AN - SCOPUS:79951694330

    VL - 36

    SP - 123

    EP - 155

    JO - Legislative Studies Quarterly

    JF - Legislative Studies Quarterly

    SN - 0362-9805

    IS - 1

    ER -