N-GrAM: New Groningen Author-profiling Model

Angelo Basile, Gareth Dwyer, Masha Medvedeva, Josine Rawee, Hessel Haagsma, Malvina Nissim

    Research output: Contribution to conferencePaperAcademic

    9 Citations (Scopus)

    Abstract

    We describe our participation in the PAN 2017 shared task on Author Profiling, identifying authors’ gender and language variety for English, Spanish, Arabic and Portuguese. We describe both the final, submitted system, and a series of negative results. Our aim was to create a single model for both gender and language, and for all language varieties. Our best-performing system (on cross-validated results) is a linear support vector machine (SVM) with word unigrams and character 3- to 5-grams as features. A set of additional features, including POS tags, additional datasets, geographic entities, and Twitter handles, hurt, rather than improve, performance. Results from cross-validation indicated high performance overall and results on the test set confirmed them, at 0.86 averaged accuracy, with performance on sub-tasks ranging from 0.68 to 0.98.
    Original languageEnglish
    Number of pages11
    Publication statusPublished - 2017
    EventConference and Labs of the Evaluation Forum (CLEF 2017): Information Access Evaluation meets Multilinguality, Multimodality, and Visualization - Trinity College, Dublin, Ireland
    Duration: 11-Sep-201714-Sep-2017

    Conference

    ConferenceConference and Labs of the Evaluation Forum (CLEF 2017)
    CountryIreland
    CityDublin
    Period11/09/201714/09/2017

    Cite this