A Survey Dataset on Bangladeshi Students' Perspectives toward Solar Energy in Educational Institutions

This mixed-method survey dataset assesses awareness, adoption, perceptions, challenges, and future recommendations regarding solar energy use in educational institutions across Bangladesh. The survey contains 19 questions and includes responses from participants representing 16 educational institutions in Bangladesh.

The dataset consists of three files: RawDataset.csv, ProcessedDataset.csv, and CTGAN_AugmentedDataset.csv. RawDataset.csv contains the original survey responses collected from participants. ProcessedDataset.csv contains the cleaned and preprocessed version of the raw data, where preprocessing techniques such as column renaming, missing value handling, normalization of responses, text normalization for free-text fields, and label encoding were applied to support accurate statistical analysis and machine learning applications. CTGAN_AugmentedDataset.csv contains the original processed data combined with additional synthetic samples generated using the Conditional Tabular Generative Adversarial Network (CTGAN) model to increase dataset size, improve data diversity, and support better machine learning model training.

This dataset can be used for statistical analysis, correlation analysis, Chi-square hypothesis testing, machine learning model development, and educational sustainability research related to solar energy awareness and adoption. The associated dataset paper will be published at ICEFronT: IEEE International Conference on Engineering and Frontier Technologies 2026.