This dataset was compiled as part of the Towards Improving Prediction Accuracy and User-Level Explainability Using Deep Learning and Knowledge Graphs: A Study on Cassava Disease study. The dataset comprises non-expert responses to a survey about the explainability of machine learning based on SHAP versus explainability based on knowledge graphs. The dataset contains the survey responses of respondents from Nigeria, Ghana, Austria, the Netherlands, and the United States of America. If you use this dataset in part or whole, please cite [1].

[1] Chhetri, T.R., Hohenegger, A., Fensel, A., Kasali, M.A. and Adekunle, A.A., 2023. Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: A study on cassava disease. Expert Systems with Applications, 233, p.120955.