University of Illinois Chicago
Browse

MithraDetective: A System for Cherry-picked Trendlines Detection.

journal contribution
posted on 2021-07-20, 16:21 authored by Yoko Nagafuchi, Yin Lin, Kaushal Mamgain, Abolfazl AsudehAbolfazl Asudeh, HV Jagadish, You Wu, Cong Yu
Given a data set, misleading conclusions can be drawn from it by cherry-picking selected samples. One important class of conclusions is a trend derived from a data set of values over time. Our goal is to evaluate whether the 'trends' described by the extracted samples are representative of the true situation represented in the data. We demonstrate MithraDetective, a system to compute a support score to indicate how cherry-picked a statement is; that is, whether the reported trend is well-supported by the data. The system can also be used to discover more supported alternatives. MithraDetective provides an interactive visual interface for both tasks.

History

Citation

Nagafuchi, Y., Lin, Y., Mamgain, K., Asudeh, A., Jagadish, H. V., Wu, Y.Yu, C. (2020). MithraDetective: A System for Cherry-picked Trendlines Detection. CoRR, abs/2010.08807. Retrieved from http://arxiv.org/abs/2010.08807v1

Usage metrics

    Categories

    No categories selected

    Keywords

    cs.DB

    Licence

    In Copyright

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC