The effect of variations of prior on knowledge tracing

Matti Nelimarkka*, Madeeha Ghori

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    1 Citation (Scopus)
    19 Downloads (Pure)

    Abstract

    Knowledge tracing is a method which enables approximation of a student's knowledge state using a Bayesian network for approximation. As the applications of this method increase, it is vital to understand the limits of this approximation. We are interested how well knowledge tracing performs when students' prior knowledge on the topic is extremely high or low. Our results indicate that the estimates become more erroneous when prior knowledge is extremely high (prior =0.90).

    Original languageEnglish
    Title of host publicationEDM 2014 Extended Proceedings
    Subtitle of host publicationProceedings of the Workshops held at Educational Data Mining 2014, co-located with 7th International Conference on Educational Data Mining (EDM 2014), London, United Kingdom, July 4-7, 2014
    EditorsSergio Gutierrez-Santos, Olga C. Santos
    Pages146-150
    Number of pages5
    Publication statusPublished - 2014
    MoE publication typeA4 Article in a conference publication
    EventInternational Conference on Educational Data Mining - London, United Kingdom
    Duration: 4 Jul 20147 Jul 2014
    Conference number: 7

    Publication series

    NameCEUR workshop proceedings
    Volume1183
    ISSN (Print)1613-0073

    Conference

    ConferenceInternational Conference on Educational Data Mining
    Abbreviated titleEDM
    CountryUnited Kingdom
    CityLondon
    Period04/07/201407/07/2014

    Keywords

    • Bayesian knowledge tracing
    • Parameter estimation
    • Personalization
    • Prior

    Fingerprint Dive into the research topics of 'The effect of variations of prior on knowledge tracing'. Together they form a unique fingerprint.

    Cite this