Radio Galaxy Zoo: #Tagging Radio Subjects using Text

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.RadioTalk是一个为射电星系动物园（Radio Galaxy Zoo, RGZ）项目的公民科学家搭建的平台，供其为所观测的射电目标补充描述信息。本数据集包含大量以标签与评论形式存在的辅助信息，这类信息对于延展射电源的研究尤为宝贵。本研究首次对该数据集展开探索，并首次结合文本与图像特征，采用机器学习方法实现射电星系的自动分类。文本标注数据较为稀缺，但却是天文源分类任务中极具价值的信息来源。