A hybrid classification method for Twitter spam detection based on differential evolution and random forest

Abstract

Summary Social networking services are online platforms that are distributed across different computers over long distances. Twitter is the most popular microblogging site that allows users to share their opinions and real‐world events. Due to its popularity and ease of use, Twitter has also attracted spammers. As a result, spam detection is one of the most critical problems. In order to provide a spam‐free environment, it is necessary to identify and filter spam tweets as well as their owners. A hybrid method, which is based on Synthetic Minority Over‐sampling TEchnique (SMOTE) and Differential Evolution (DE) strategies, is presented to enhance the spam detection rate in real Twitter datasets. SMOTE is applied to tackle the imbalanced class distribution of datasets, while DE is used to tune Random Forest (RF) hyperparameters. Compared with related work and based on evaluation results, the presented method significantly enhances the classification performance in imbalanced datasets. The detection rate of optimized RF with excellent F1‐score and Area Under the Receiver Operating Characteristic Curve (AUROC), which are 98.97% and 0.999, respectively, demonstrates the high efficiency of the proposed method.

Flood Hazard Assessment in Australian Tropical Cyclone-Prone Regions

“…Differential evolution (DE), developed by [67], has been used in the past as an effective strategy for hyperparameter optimisation for RF algorithms, balancing the exploration and exploitation of the search space. As described in [68], the DE optimisation works by creating a population of "models", training them, and then assessing them on the basis of an objective scoring function. Then the population is iterated each generation.…”

TF-IDF Weighting to Detect Spammer Accounts on Twitter based on Tweets and Retweet Representation of Tweets

“…Popularitas Twitter tersebut menarik pengguna yang tidak bertanggung jawab untuk melakukan kegiatan spam [4]. Spam merupakan pesan yang dikirimkan oleh pengguna (Spammer) ke pengguna lain secara bertubi-tubi.…”

Prediction Retweet Using User-Based and Content-Based with ANN-GA Classification Method

“…Genetic Algorithm has several phases in solving the problems experienced, namely initiation which is the first stage to get new individuals who will later become solutions to problems or programs that are being built [10]. Next grouping, offspring will be grouped into one The next stage is the evaluation stage to calculate individual value in offspring or parent, and finally, selection is a process to select individuals from offspring and parent, the best value will be passed to the next generation or can be a solution [14]. Mutation is a random change that an individuals genes undergo and mutation is the most important factor in evolution which allows you to find new solution [16].…”