Reproducing affective norms with lexical co-occurrence statistics: Predicting valence, arousal, and dominance

M.M. Louwerse, G. Recchia

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    Human ratings of valence, arousal, and dominance are frequently used to study the cognitive mechanisms of emotional attention, word recognition, and numerous other phenomena in which emotions are hypothesized to play an important role. Collecting such norms from human raters is expensive and time consuming. As a result, affective norms are available for only a small number of English words, are not available for proper nouns in English, and are sparse in other languages. This paper investigated whether affective ratings can be predicted from length, contextual diversity, co-occurrences with words of known valence, and orthographic similarity to words of known valence, providing an algorithm for estimating affective ratings for larger and different datasets. Our bootstrapped ratings achieved correlations with human ratings on valence, arousal, and dominance that are on par with previously reported correlations across gender, age, education and language boundaries. We release these bootstrapped norms for 23,495 English words.
    Original languageEnglish
    Article number941296
    Pages (from-to)1-15
    Number of pages16
    JournalThe Quarterly Journal of Experimental Psychology
    Volume68
    Issue number12
    Early online date10 Sep 2014
    DOIs
    Publication statusPublished - 10 Sep 2014

    Fingerprint

    Language
    Education

    Keywords

    • Affective norms
    • Valence
    • Arousal, Dominance
    • Latent Semantic Analysis

    Cite this

    @article{67f8134f6a04407fa24a375916ec3471,
    title = "Reproducing affective norms with lexical co-occurrence statistics: Predicting valence, arousal, and dominance",
    abstract = "Human ratings of valence, arousal, and dominance are frequently used to study the cognitive mechanisms of emotional attention, word recognition, and numerous other phenomena in which emotions are hypothesized to play an important role. Collecting such norms from human raters is expensive and time consuming. As a result, affective norms are available for only a small number of English words, are not available for proper nouns in English, and are sparse in other languages. This paper investigated whether affective ratings can be predicted from length, contextual diversity, co-occurrences with words of known valence, and orthographic similarity to words of known valence, providing an algorithm for estimating affective ratings for larger and different datasets. Our bootstrapped ratings achieved correlations with human ratings on valence, arousal, and dominance that are on par with previously reported correlations across gender, age, education and language boundaries. We release these bootstrapped norms for 23,495 English words.",
    keywords = "Affective norms, Valence, Arousal, Dominance, Latent Semantic Analysis",
    author = "M.M. Louwerse and G. Recchia",
    year = "2014",
    month = "9",
    day = "10",
    doi = "10.1080/17470218.2014.941296",
    language = "English",
    volume = "68",
    pages = "1--15",
    journal = "The Quarterly Journal of Experimental Psychology",
    issn = "1747-0218",
    publisher = "ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD",
    number = "12",

    }

    Reproducing affective norms with lexical co-occurrence statistics : Predicting valence, arousal, and dominance. / Louwerse, M.M.; Recchia, G.

    In: The Quarterly Journal of Experimental Psychology, Vol. 68, No. 12, 941296, 10.09.2014, p. 1-15.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Reproducing affective norms with lexical co-occurrence statistics

    T2 - Predicting valence, arousal, and dominance

    AU - Louwerse, M.M.

    AU - Recchia, G.

    PY - 2014/9/10

    Y1 - 2014/9/10

    N2 - Human ratings of valence, arousal, and dominance are frequently used to study the cognitive mechanisms of emotional attention, word recognition, and numerous other phenomena in which emotions are hypothesized to play an important role. Collecting such norms from human raters is expensive and time consuming. As a result, affective norms are available for only a small number of English words, are not available for proper nouns in English, and are sparse in other languages. This paper investigated whether affective ratings can be predicted from length, contextual diversity, co-occurrences with words of known valence, and orthographic similarity to words of known valence, providing an algorithm for estimating affective ratings for larger and different datasets. Our bootstrapped ratings achieved correlations with human ratings on valence, arousal, and dominance that are on par with previously reported correlations across gender, age, education and language boundaries. We release these bootstrapped norms for 23,495 English words.

    AB - Human ratings of valence, arousal, and dominance are frequently used to study the cognitive mechanisms of emotional attention, word recognition, and numerous other phenomena in which emotions are hypothesized to play an important role. Collecting such norms from human raters is expensive and time consuming. As a result, affective norms are available for only a small number of English words, are not available for proper nouns in English, and are sparse in other languages. This paper investigated whether affective ratings can be predicted from length, contextual diversity, co-occurrences with words of known valence, and orthographic similarity to words of known valence, providing an algorithm for estimating affective ratings for larger and different datasets. Our bootstrapped ratings achieved correlations with human ratings on valence, arousal, and dominance that are on par with previously reported correlations across gender, age, education and language boundaries. We release these bootstrapped norms for 23,495 English words.

    KW - Affective norms

    KW - Valence

    KW - Arousal, Dominance

    KW - Latent Semantic Analysis

    U2 - 10.1080/17470218.2014.941296

    DO - 10.1080/17470218.2014.941296

    M3 - Article

    VL - 68

    SP - 1

    EP - 15

    JO - The Quarterly Journal of Experimental Psychology

    JF - The Quarterly Journal of Experimental Psychology

    SN - 1747-0218

    IS - 12

    M1 - 941296

    ER -