Skip to content

LeitnerQ Mechanical Turk Data and Code Release

Element · All elements
Evidence · no claims cited

Description

The authors release their model, evaluation and user-study code plus their experiment data: "we release (1) all model and evaluation code, (2) framework code for carrying out user studies, and (3) the data collected in our Mechanical Turk study". The Mechanical Turk data set holds 77,034 logs from 331 unique users and 446 unique items, with an overall recall rate of 0.663 and fixed 15-minute sessions.

Design Implications

Context

Requirements

  • A flashcard interface where the user guesses a foreign-language item's translation, sees the answer, and self-assesses on a 1-4 scale, with 3 or 4 counted as a pass.

Constraints

Target Learners

  • Mechanical Turk workers learning Japanese words or American Sign Language gestures

Target Learning Goals

  • Foreign-language vocabulary memorization
  • Replication and follow-up studies of spaced repetition scheduling

Affordances

Claims

Examples

-

Key Sources

  • Reddy, S., Labutov, I., Banerjee, S., & Joachims, T. (2016). Unbounded Human Learning: Optimal Scheduling for Spaced Repetition. KDD ’16, San Francisco, CA, USA. https://doi.org/10.1145/2939672.2939850
Page metadata
Field Value
type element
id leitnerq-mturk-data-and-code-release
title LeitnerQ Mechanical Turk Data and Code Release
description The authors release their model, evaluation and user-study code plus their experiment data: "we release (1) all model and evaluation code, (2) framework code for carrying out user studies, and (3) the data collected i...
status review
canonical True
generated by claude/unspecified on 2026-09-24
trust unverified — no one has confirmed this page's content
sources 1 — reddy-2016

Frontmatter is the page's machine-readable record — see the Schema & Guide.