Prediction of Emerging Communities-Related Data

This dataset contains preprocessed vocabulary functional category information, community basic information, community feature set, and prediction result information. 1. Vocabulary functional category information: Table 1_ Ehealth_ Lexical_ Function.csv describes the functional attribute category information of all vocabulary in the corpus. 2. Basic information of the community: Table 2_ Community_ Info.csv describes the determination information of whether a community belongs to a hot or emerging community, as well as the year, node, and edge related statistical information of the community. 3. Community feature set: Table 3_ Community_ Features_ Input.csv describes the specific indicator values of all features of a community, used for predicting model training and testing. 4. Prediction result data: Table 4_ Prediction_ Consequence describes the accuracy, precision, recall, and F1 score of five prediction models under different feature combinations