Published March 30, 2023
| Version 1.0.0
Dataset
Open
Radio Galaxy Zoo: #Tagging Radio Subjects using Text
- 1. Australian National University
- 2. University of Western Australia
- 3. Google Australia
- 4. CSIRO Space & Astronomy
- 5. Data61, CSIRO
Description
RadioTalk is a platform that enabled citizen scientists of the Radio Galaxy Zoo (RGZ) project to provide additional descriptions of the radio subjects they were observing. This dataset contains a wealth of auxiliary information in the form of tags and comments which are especially valuable for extended radio sources. Our work is the first to explore this dataset, and for the first time, we combine text and image features to automatically classify radio galaxies using a machine learning approach. Text annotations are rare but valuable sources of information for the classification of astronomical sources.
Notes
data_train.zip: compressed csv file for training data.
data_val.zip: compressed csv file for validation data.
data_test.zip: compressed csv file for test data.
Each row in the csv file corresponds to a radio subject. Columns corresponds to features and tags: radio image features (column radio001 to column radio768), infrared image features (column ir001 to column ir768), RadioTalk discussion text features (column text001 to column text768), and boolean indicator of tags (the last 11 columns).