TextNetTopics: Text Classification based Word Grouping as Topics and Topics' Scoring Malik Yousef1* and Daniel Voskergian2* 1Zefat Academic College, Israel 2Al-Quds University, Palestine Medical document classification is one of the active research problems and the most challenging within the text classification domain. Medical datasets often contain massive feature sets where many features are considered irrelevant, redundant, and add noise, which reduces considerably the classification performance. Thus, to obtain a better accuracy of a classification model, it is crucial to choose a set of features that best discriminate between the classes of medical documents. In this study, we propose TextNetTopics, a novel approach that applies feature selection by considering Bag-of-topics (BOT) rather than the traditional approach, Bag-of-words (BOW). Thus our approach performs topic selections rather than words selection. TextNetTopics is based on the generic approach called G-S-M (Grouping, Scoring, and Modeling), developed by Yousef and his colleagues, where it is used mainly in biological data. The proposed approach suggests scoring topics to select top topics for training the classifier. In this study, we applied TextNetTopics on textual data as a response to the CAMDA challenge. The performance of TextNetTopics outperforms other feature selection approaches while getting a high performance when applying the model on the validation data provided by the CAMDA. Additionally, we have applied our algorithm in different textual datasets.