Organized Behavior Classification of Tweet Sets using Supervised Learning Methods

Abstract

During the 2016 US elections Twitter experienced unprecedented levels of propaganda and fake news through the collaboration of bots and hired persons, the ramifications of which are still being debated. This work proposes an approach to identify the presence of organized behavior in tweets. The Random Forest, Support Vector Machine, and Logistic Regression algorithms are each used to train a model with a data set of 850 records consisting of 299 features extracted from tweets gathered during the 2016 US presidential election. The features represent user and temporal synchronization characteristics to capture coordinated behavior. These models are trained to classify tweet sets among the categories: organic vs organized, political vs nonpolitical, and pro-Trump vs pro-Hillary vs neither. The random forest algorithm performs better with greater than 95% average accuracy and f-measure scores for each category. The most valuable features for classification are identified as user based features, with media use and marking tweets as favorite to be the most dominant.

Hybrid model for early identification post-Covid-19 sequelae

“…Tom M. Mitchell, the principal exponent in ML, explains: “Machine learning is the study of computer algorithms that allow computer programs to improve with the experience” (Turban et al 2011 ; Mitchell 2011 ) automatically. Machine Learning leads to Artificial Intelligence and depends on working with data sets, examining common patterns, and exploring complaints (Beğenilmiş and Uskudarl 2018 ; Mitchell 1997 ). The learning of the algorithms happens autonomously over time, according to the analysis of the training data.…”

An Intelligent Multicriteria Model for Diagnosing Dementia in People Infected with Human Immunodeficiency Virus

“…The bagging procedures and the Classification and Regression Trees (CART) division criteria critically analyze the Random Forest [35]. Like a bootstrap aggregation contraction, bagging is a general grouping scheme that proceeds by generating subsamples from the original data set, building a predictor for each sample and deciding on the mean.…”

Detection of malicious social bots: A survey and a refined taxonomy

“…Crossover botnets have following relationships in both directions between bots and normal users. Begenilmiş and Uskudarli (2018) distinguished between (organized-vs. organic-behavior), (pro-Trump vs. pro-Hillary vs none) and (political vs. nonpolitical). Gao et al (2010) focused on detecting malicious (URL/posts).…”

“…The best results were achieved using J48 decision tree algorithm. Begenilmiş and Uskudarli (2018) proposed supervised ML-based detection of organized behavior based on RF, SVM, and LR approaches. They employed user and temporal features to distinguish between three categories: organized-vs. organic-behavior, pro-Trump vs. pro-Hillary vs none and political vs. nonpolitical.…”

“…Even though they may involve in a malicious activity, all real users' accounts (such as human spammers, trolls, managed accounts) are not social bots. Stringhini et al (2010) Begenilmiş and Uskudarli (2018) distinguished between (organized-vs. organic-behavior), (pro-Trump vs. pro-Hillary vs none) and (political vs. nonpolitical). Gao et al (2010) focused on detecting malicious (URL/posts).…”