Loading...
Loading...
Student performance, MOOC logs, knowledge tracing, standardized tests, learning analytics
12,731 datasets
A perspective paper by Anna Meduri, uploaded to figshare on 2026-04-17, critically examines the conceptualization and measurement of engagement and motivation in technology-based interventions for Autism Spectrum Disorder (ASD). The 19.7 KB document argues that outcomes often labeled as engagement may primarily index sustained attention, driven by features like predictable structure and immediate feedback. It proposes improving conceptual precision to better interpret how technology modulates attention, motivation, and participation in autistic individuals.
5.5 KB of example participant responses to a prompt probing the experience of applying session learnings in day-to-day life. The dataset was authored by Samuel Downes and is available under a CC-BY-4.0 license. It was last updated on 2026-05-27.
Example participant responses to prompts probing experience of attending a programme session. The dataset is a 5.5 KB XLS file authored by Samuel Downes and shared under a CC-BY-4.0 license. It was last updated on May 27, 2026.
Ya-En Catherine Lin's dataset explores the relationships between ad recognition, advertising literacy, and purchase intention. The data is stored in a 9.5 KB XLS file and was last updated on May 27, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
A 5.5 KB Excel dataset by Ya-En Catherine Lin, last updated on 2026-05-27. The data examines how different types of disclosures affect consumer advertising literacy and purchase intention.
5.5 KB of sensitivity analyses in an XLS file, examining adjusted associations between varying metrics of objective cannabis outlet availability and cannabis outcomes. The dataset was authored by Vi T. Le and last updated on May 27, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
Western Australia's offshore hydrocarbon potential is assessed for the Tithonian play in the Dampier Sub-basin and Rankin Trend. The assessment includes results from six wells, including the Angel gas and Egret oil discoveries, and uses Monte Carlo simulation to evaluate four undrilled prospects. The dataset originates from the Australian Ocean Data Network.
Raw data used for researching Dynamic Multi-Dimensional Contract Design for Incentivized Edge Federated Learning. The dataset is 86.2 MB in size, stored in CSV format, and was last updated on May 22, 2026. It was authored by Qian and is shared under a CC-BY-4.0 license.
Cambodia's road network, covering approximately 122,600 kilometers, is classified by surface type using a hybrid deep learning approach. The dataset, created by HeiGIT, combines OpenStreetMap data with AI predictions from Mapillary imagery and urban layers from GHSU and AFRICAPOLIS. It was last updated on March 2, 2026.
A geospatial dataset provides detailed information on road surfaces in Nicaragua, distinguishing between paved and unpaved roads. The data originates from OpenStreetMap and is augmented with deep learning predictions based on Mapillary imagery and urban classification layers. It was last updated on 2026-03 02 by the Heidelberg Institute for Geoinformation Technology (HeiGIT).
A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides AI-derived road surface classifications for Yemen. It covers approximately 122,500 kilometers of roads from OpenStreetMap, distinguishing paved and unpaved surfaces using a hybrid deep learning method. The data is augmented with predictions from Mapillary imagery and urban layers.
Niger's road network, comprising approximately 296,700 kilometers of mapped roads, is classified by surface type using a hybrid deep learning approach. The dataset, created by HeiGIT and last updated in March 2026, distinguishes paved from unpaved roads and integrates OpenStreetMap data with predictions from Mapillary imagery. It includes AI-derived features like predicted class and length, along with standard OSM attributes.
HeiGIT's dataset provides AI-derived road surface classifications for Azerbaijan, distinguishing paved and unpaved roads. It covers approximately 0.1237 million km of roads mapped in OpenStreetMap, with deep learning predictions augmenting missing surface data. The dataset was last updated on March 2, 2026.
A geospatial dataset detailing road surfaces across Italy, distinguishing paved and unpaved roads. It contains approximately 1.48 million kilometers of roads from OpenStreetMap, augmented with AI-derived surface predictions from Mapillary imagery. The dataset was created by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and was last updated in March 2026.
A 2026 dataset from the Heidelberg Institute for Geoinformation Technology (HeiGIT) provides AI-derived road surface classifications for the Seychelles. It distinguishes paved and unpaved roads using a hybrid deep learning approach on OpenStreetMap data, augmented with Mapillary imagery and urban layers. The data indicates approximately 0.0014 million km of roads are mapped, with AI estimates for paved (0.0002 million km) and unpaved (0.0001 million km) segments.
A geospatial dataset from HeiGIT details road surfaces in Chad, distinguishing paved from unpaved roads. It covers approximately 0.2286 million kilometers of roads, with AI-derived estimates classifying 3.3918% as paved and 46.3487% as unpaved. The data, last updated in March 2026, combines OpenStreetMap features with deep learning predictions from Mapillary imagery and urban classification layers.
Cayman Islands road network data distinguishes paved and unpaved surfaces using a hybrid deep learning approach. The dataset, created by HeiGIT, covers approximately 1.3 km of roads mapped in OpenStreetMap, with AI-derived estimates classifying 44.5% as paved and 11.2% as unpaved. It was last updated in March 2026.
Madagascar road network data from OpenStreetMap, enhanced with AI-derived surface classifications. The dataset covers approximately 0.5261 million kilometers of roads, with deep learning predictions distinguishing paved and unpaved surfaces. It was created by HeiGIT and last updated in March 2026.
New Zealand road network data provides AI-derived surface classifications for approximately 232,500 kilometers of roads. The dataset, created by HeiGIT, combines OpenStreetMap (OSM) attributes with deep learning predictions from Mapillary imagery and urban classification layers. It was last updated on March 2, 2026.
A geospatial dataset detailing road surfaces across India, derived from OpenStreetMap and augmented with AI predictions from street-level imagery. The dataset covers approximately 4.8 million kilometers of roads, with AI-derived estimates classifying 0.53 million km as paved and 0.29 million km as unpaved. It was created by the Heidelberg Institute for Geoinformation Technology (HeiGIT) and last updated in March 2026.