About this table

Description	Modeling of second language acquisition, data from English learners (who already speak Spanish).
Reference	Settles, Burr, 2018, "Data for the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM)", https://doi.org/10.7910/DVN/8SWHNO, Harvard Dataverse, V4, https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/8SWHNO
Licence	CC BY 4.0
Source data	http://sharedtask.duolingo.com/2018.html#task-definition-data

Size and shape

Responses	1,173,244
Respondents	2,593
Items	21,621
Response categories	2
Responses per respondent	452.466
Responses per item	54.264
Density	0.021
Longitudinal	FALSE

Classification

sample	General/non-specific
construct type	Cognitive/educational
measurement tool	Test
item format	Constructed Response
primary language(s)	eng, spa
construct name	reverse_translate

Codebook

This codebook is reconstructed by the IRW from the IRW data standard and the script that built it, duolingo2018.R. It is our best reading, not the source’s own codebook, and it may contain mistakes. Where the two disagree, the source data are the authority. If you find an error, please tell us.

Column	What it is	Source column
IRW standard columns
`id`	IRW standard Identifier for the focal unit being measured — typically a person, but sometimes another entity (e.g., a word in a lexical task).	made in the build script
`item`	IRW standard Item identifier.	made in the build script
`resp`	IRW standard Response value.	made in the build script
`rt`	IRW standard Response time.	made in the build script
Other columns
`dependency_head`	Not documented Not documented by the IRW; see the source’s codebook.	not traced
`dependency_label`	Not documented Not documented by the IRW; see the source’s codebook.	not traced
`format`	Not documented Not documented by the IRW; see the source’s codebook.	made in the build script
`morphology`	Not documented Not documented by the IRW; see the source’s codebook.	made in the build script
`part_speech`	Not documented Not documented by the IRW; see the source’s codebook.	not traced
`session`	Not documented Not documented by the IRW; see the source’s codebook.	made in the build script
`stem`	Not documented Not documented by the IRW; see the source’s codebook.	made in the build script

What item codes and covariate values stand for is in the codebook released with the source data.

Get the data

Browse on Redivissign in to download

This table is larger than Redivis serves as a CSV without a login. The R package below downloads it with no account; the Python package and the Redivis website need you to sign in to Redivis.

Or load it directly in R or Python:

# R (no account needed)
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("duolingo_en_es__reverse_translate")

# Python (needs a free Redivis account)
pip install irw

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

How to cite

@misc{https://doi.org/10.7910/dvn/8swhno,
  doi = {10.7910/DVN/8SWHNO},
  url = {https://dataverse.harvard.edu/citation?persistentId=doi:10.7910/DVN/8SWHNO},
  author = {{Settles, Burr}},
  keywords = {Computer and Information Science, Social Sciences, Duolingo, Spaced Repetition, Second Language Acquisition, Machine Learning, Computational Linguistics},
  title = {Data for the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM)},
  publisher = {Harvard Dataverse},
  year = {2018}
}

Version and provenance

IRW version	v540
Redivis dataset	item_response_warehouse v70.0
Redivis dataset DOI	10.57761/4qxs-pq87
Manifest pin for this IRW version	v70.0
Metadata source	irw_meta v37.0

duolingo_en_es__reverse_translate