neurips_2020_task34

1,508,917 responses from 6,148 respondents to 948 items.

About this table

DescriptionResponses to the 948 diagnostic mathematics questions of the NeurIPS 2020 Education Challenge tasks 3 and 4 (question quality and personalisation). Split out from neurips_2020, which holds the tasks 1/2 release: the challenge anonymised the two releases separately and its guide (arXiv:2007.12061, p.8) states that question, user and answer IDs must not be linked between them, so they cannot share an id or item space. resp is 1 if the student answered correctly. See irw#1875.
ReferenceWang, Z., Lamb, A., Saveliev, E., Cameron, P., Zaykov, Y., Hernández-Lobato, J.M., Turner, R.E., Baraniuk, R.G., Barton, C., Jones, S.P., Woodhead, S., & Zhang, C. (2020). Diagnostic questions: The neurips 2020 education challenge [data set]. arXiv preprint arXiv:2007.12061
DOI10.48550/arXiv.2007.12061
LicenceCC BY 4.0
Source datahttps://eedi.com/research#data

Size and shape

Responses1,508,917
Respondents6,148
Items948
Response categories2
Responses per respondent245.432
Responses per item1591.685
Density0.259
LongitudinalFALSE

Classification

age rangeChild (<18y)
child age (for child-focused studies)Child (6-12y)
sampleEducational
construct typeCognitive/educational
measurement toolTest
item formatLikert Scale/selected response
primary language(s)eng
construct nameNeurIPS 2020 Education Challenge (tasks 3/4)

Columns

iditemresp

Get the data

Download CSVno account neededBrowse on Redivisexplore and queryCroissant metadataHugging Face, Kaggle, OpenML

Or load it directly in R or Python:

# R
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("neurips_2020_task34")
# Python
pip install irw

import irw
df = irw.fetch("neurips_2020_task34")

Version and provenance

IRW versionv393
Redivis datasetitem_response_warehouse_6 v2.1
Redivis dataset DOI10.57761/fr6e-wp05
Manifest pin for this IRW versionv2.1
Metadata sourceirw_meta v23.0