Summary Online social networks such as Facebook and Twitter have become part of our daily lives. Their influence on business, politics, and society is considerable. Sensitive or unreliable information can adversely affect individuals, organizations, and governments. Due to the effects of the Covid‐19 epidemic, online news is more plentiful and accessible, which raises concerns about its reliability, quality, and authenticity. This article proposes the use of population dynamics model to study information dissemination on Facebook and a Susceptible‐Infected‐Recovered (SIR) model to examine information propagation as an outbreak of disease. We investigated 27 datasets with more than 270,000 messages, and the experiments showed that the population dynamics model is suitable for modeling the spread of information. The results revealed that information propagation could occur rapidly; after only 1–2 days. Additionally, we discovered that it is very crucial to find immediate solutions for preventing fake information as soon as it appears. This work enables us to understand the mechanism of information dissemination on social networks. This can help control and prevent the spread of misleading information, avoiding unintended consequences.

Abstract The stock forecast is one of the most challenging tasks that have attracted numerous economists and scientists worldwide. Stock prices can be affected by many reasons, such as physiological, rational, and irrational behavior. Such factors can combine to make the prices volatile and very challenge to predict with great accuracy for a long time in numerous cases. In this study, we have deployed a long short‐term memory architecture with various time‐steps and classic machine learning methods such as random forests, support vector machines, and autoregression on the Taiwanese stock market collected in 14–15 years. As shown from the visual results, the predicted values have followed the patterns as the actual prices with low error rates in various metrics, including root mean square error and mean absolute error. This work is expected to provide a valuable tool for investigating stock price patterns of stock markets in the future.

Feature selection is used to preserve significant properties of data in a compact space. In particular, feature selection is needed in applications, where information comes from multiple heterogeneous high dimensional sources. Data integration, however, is a challenge in itself. In our contribution, we introduce a feature selection framework based on powerful visualisation capabilities of self-organising maps, where the deep structure can be learned in a supervised or unsupervised manner. For a supervised version of the deep SOM, we propose to carry out inference with a linear SVM. A forward-backward procedure helps to converge to an optimal feature set. We show by experiments on real large-scale biomedical data set that the proposed methods embed data in a new compact meaningful representation, allow to visualise biomedical signatures, and also lead to a reasonable classification accuracy compared to the state-of-the-art methods.