Self-labelling tutoring tool dataset: 7 students, 40 fraction/arithmetic tasks, 280 self-labelled tasks with log-file recording

Product or Programme · All products and programmes
Evidence · 4 claims (4 for) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 4 claims rest on one study

Description

A dataset created by Ruth Janning et al. containing timestamped interaction logs and student self-labels of perceived difficulty from 280 fraction and arithmetic practice tasks.

Components

• Self-labelling tutoring tool dataset: 7 students, 40 fraction/arithmetic tasks, 280 self-labelled tasks with log-file recording: A dataset from a study in which "7 students in the age of 21 – 28 each had to solve 40 mathematical tasks and to label at the end of a task the perceived task-difficulty themselves by means of the small offline self-labelling tutoring java tool". "Each of the 7 students has seen all 40 tasks resulting in 280 labelled tasks", distributed as 40 too hard, 20 hard, 93 appropriate, 121 easy and 6 too easy. The tool is a drill-and-practice math system that does not model student knowledge but provides only the log-file data and labels; every action was written with a time stamp into a log file. (Ruth Janning et al. (2016))

Claims

• Single log-file features per task show very small p-values but weak fit, with number of hints seen the strongest single predictor of perceived task-difficulty. [+W]
• Log-file features are suitable for recognising perceived task-difficulty per task, with SVM the best single classifier (25.24% average test error). [+W]
• A two-feature combination of average time until skip and average time until first hint request statistically significantly describes students' accumulated perceived task-difficulty across a learning session. [+W]
• The generalised plait ensemble outperforms single classifiers, majority-vote and stacking ensembles, substantially improving perceived task-difficulty classification (e.g., SVM plait error 14.54%, KNN plait 12.84%). [+W]

Related Products and Programmes

-

Key Sources

• Ruth Janning, Carlotta Schatten, Lars Schmidt-Thieme. (2016). Perceived Task-Difficulty Recognition from Log-file Information for the Use in Adaptive Intelligent Tutoring Systems. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-016-0097-9

Page metadata

Field	Value
type	product
id	self-labelling-tutoring-tool-dataset-7-students-40-fractionarithmetic-tasks-280-self-label
title	Self-labelling tutoring tool dataset: 7 students, 40 fraction/arithmetic tasks, 280 self-labelled tasks with log-file recording
description	A dataset created by Ruth Janning et al.
status	review
product_kind	dataset
generated	by process:settle-candidates on 2026-10-27
trust	unverified — no one has confirmed this page's content

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