Machine learning Bot detection technique, based on United States election dataset

Overview

Machine learning Bot detection technique, based on United States election dataset (2020).

Current github repo provides implementation described in paper: "Identification of Twitter Bots based on an Explainable ML Framework: the US 2020 Elections Case Study" accepted in ICWSM 2022 conference.

Code folder contain all scripts for:

  • feature selection
  • parameter fine tuning
  • final model performance evaluation

Developed Bot Detection ML framework was trained and tested over Twitter dataset.
The particular dataset was collected with use of Twitter API during the 2020 US Election period. During this period we manage to collect tweets/retweets that contain particular hashtags that are correlated with the 2020 US Election topic. We provide our dataset in the form of two separated files. In those files we provide already extracted features for each user that was labeled according to our labeling process.

  1. data/us_2020_election_data.csv
    • contain user features and labels that was active in twitter during the month of September
    • we utilize it during our training/validation/testing phase of our implementation
  2. data/us_2020_election_data_october.csv
    • is utilized in order to identify how a developed model can perform over the unseen data that was collected during the month of October.

Both files was labeled with use of Botometer and BotSentinel Bot Detection tools. We keep only a union of users where both tools agree if a particular account is bot or normal user. Created pipeline allow us to keep user labels as clear as possible. We remove user ids in order to keep private the user identity, we provide only labels and extracted features which do not provide any sensitive user information.

In the plot folder we store performance metrics results in the form of figures.

Execution flow:

  1. code/feature_selection.py
    • Provide file with selected features in code folder
  2. code/model_fine_tuning.py
    • Store parameters of best model after the fine-tuning
  3. code/performance_measurement.py
    • Evaluate selected model and generates figures of ROC and PR AUCs. Also provide SHAP figure that explain the model decision making based on 20 most important features.

Developed framework provides state of the art performance over the Twitter US Election data. Based on the performance of unseen data we assume that is possible utilization of developed methods over data more than one month after training data, since the performance drop is not significant.

You might also like...
An experimental technique for efficiently exploring neural architectures.
An experimental technique for efficiently exploring neural architectures.

SMASH: One-Shot Model Architecture Search through HyperNetworks An experimental technique for efficiently exploring neural architectures. This reposit

Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

SMU A Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE arXiv https://arxiv.org/abs/211

This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

Machine Learning Hand Detector This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Dev

This project deals with the detection of skin lesions within the ISICs dataset using YOLOv3 Object Detection with Darknet.
This project deals with the detection of skin lesions within the ISICs dataset using YOLOv3 Object Detection with Darknet.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Skin Lesion detection using YOLO This project deal

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

Machine Learning From Scratch About Python implementations of some of the fundamental Machine Learning models and algorithms from scratch. The purpose

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

This is the Vowpal Wabbit fast online learning code. Why Vowpal Wabbit? Vowpal Wabbit is a machine learning system which pushes the frontier of machin

MOT-Tracking-by-Detection-Pipeline - For Tracking-by-Detection format MOT (Multi Object Tracking), is it a framework that separates Detection and Tracking processes?
Sub-tomogram-Detection - Deep learning based model for Cyro ET Sub-tomogram-Detection

Deep learning based model for Cyro ET Sub-tomogram-Detection High degree of stru

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

Master status: Development status: Package information: TPOT stands for Tree-based Pipeline Optimization Tool. Consider TPOT your Data Science Assista

Owner
Alexander Shevtsov
PhD candidate in Computer Science
Alexander Shevtsov
Interpretation of T cell states using reference single-cell atlases

Interpretation of T cell states using reference single-cell atlases ProjecTILs is a computational method to project scRNA-seq data into reference sing

Cancer Systems Immunology Lab 139 Jan 3, 2023
This project uses Template Matching technique for object detecting by detection of template image over base image.

Object Detection Project Using OpenCV This project uses Template Matching technique for object detecting by detection the template image over base ima

Pratham Bhatnagar 7 May 29, 2022
This project uses Template Matching technique for object detecting by detection of template image over base image

Object Detection Project Using OpenCV This project uses Template Matching technique for object detecting by detection the template image over base ima

Pratham Bhatnagar 4 Nov 16, 2021
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)

PyExplainer PyExplainer is a local rule-based model-agnostic technique for generating explanations (i.e., why a commit is predicted as defective) of J

AI Wizards for Software Management (AWSM) Research Group 14 Nov 13, 2022
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)

PyExplainer PyExplainer is a local rule-based model-agnostic technique for generating explanations (i.e., why a commit is predicted as defective) of J

AI Wizards for Software Management (AWSM) Research Group 14 Nov 13, 2022
Dataset used in "PlantDoc: A Dataset for Visual Plant Disease Detection" accepted in CODS-COMAD 2020

PlantDoc: A Dataset for Visual Plant Disease Detection This repository contains the Cropped-PlantDoc dataset used for benchmarking classification mode

Pratik Kayal 109 Dec 29, 2022
CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.

CoReNet CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image. It produces coherent reconstructions, where all objec

Google Research 80 Dec 25, 2022
Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

AngularGrad Optimizer This repository contains the oficial implementation for AngularGrad: A New Optimization Technique for Angular Convergence of Con

mario 124 Sep 16, 2022
Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

ODE GAN (Prototype) in PyTorch Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary

Somshubra Majumdar 15 Feb 10, 2022