Geometric Deep Lean Learning: Evaluation Using a Twitter Social Network

Abstract

The goal of this work is to evaluate a deep learning algorithm that has been designed to predict the topological evolution of dynamic complex non-Euclidean graphs in discrete–time in which links are labeled with communicative messages. This type of graph can represent, for example, social networks or complex organisations such as the networks associated with Industry 4.0. In this paper, we first introduce the formal geometric deep lean learning algorithm in its essential form. We then propose a methodology to systematically mine the data generated in social media Twitter, which resembles these complex topologies. Finally, we present the evaluation of a geometric deep lean learning algorithm that allows for link prediction within such databases. The evaluation results show that this algorithm can provide high accuracy in the link prediction of a retweet social network.

Topic Modeling and Sentiment Analysis of Online Education in the COVID-19 Era Using Social Networks Based Datasets

“…the first point leads to the fact that each person in a network has attributes and those attributes can make changes to, or can be changed by, the social environment. The second point confirms that the flow of information is what produces complex networks, or what we call a "living network" [43,45].…”

“…Developing more complex networks with more hidden layers, more inputs, and various networks' parameters, to enhance neural networks' performance, warrants further investigation, which leads to learning more useful and complex representations in neural networks. The main goal of this work is to predict fake news and misinformation for the education sector during various periods of the year [42,43].…”

Link Prediction in Time Varying Social Networks

“…In fact, online users tend to acquire information adhering to their worldviews [36], ignoring dissenting information [37] that increases the probability of the spreading of misinformation [38], which may cause fake news and inaccurate information to spread faster and wider than fact-based news [39]. In [40], the authors study a Twitter's retweet network using geometric deep learning. Leng at al.…”