Magazines | Journals | Books and Articles

The IUP Journal of Information Technology

Black Lives Matter: Exploratory Analysis of Social Media Disclosures

Article Details

Pub. Date	: Dec, 2022
Product Name	: The IUP Journal of Information Technology
Product Type	: Article
Product Code	: IJIT031222
Author Name	: A C Nanayakkara and G A D M Thennakoon
Availability	: YES
Subject/Domain	: Engineering
Download Format	: PDF Format
No. of Pages	: 18

Price

Download

Abstract

Social media has become a contemporary platform for vox populi, enriched with the facilities of almost unrestricted access and versatility in terms of time and location of the users. The behaviors of social media users are creating a plethora of data, and is a fertile ground for Exploratory Data Analysis (EDA), which enables users to discover the veiled story within the datasets often using visual methods. This study focuses on the tragic incident of George Floyd's death that took place on May 25, 2020, in Minneapolis, Minnesota, US, in terms of the social media responses by analyzing the corpus of comments for a selected YouTube video. Python programming language has been used to implement the EDA process using the methods of Text statistics analysis, Sentiment analysis, Ngram exploration, Topic modeling, Parts of Speech (POS) tagging, Word cloud formation, Named Entity Recognition (NER) and Text complexity analysis. By exploring the video disclosure with relevant tools, the study provides insights on the netizens, their behavior and their influence on society. This endeavor will help in preventing the manipulation of public opinion.

Introduction

Contemporary interpersonal communication becomes decisive in online environments due to an almost unrestricted, time and location-independent accessibility. Social networks, (micro-) blogs and instant messaging services equip their users with several features to communicate and disclose content, such as sharing photos, videos or status updates with friends or the public. Therefore, these platforms have acquired immense significance for individuals to fulfill personal needs (Huang et al., 2014; and Wegmann et al., 2017). The exploratory analysis of this enormous amount of social data is also alluring for companies, scientists, economists, researchers and even politicians looking for insights into invisible areas (Sahoo et al., 2019). In data mining, Explorative Data Analysis (EDA) is a method for reviewing datasets to highlight their key features, often with visual aids before the modeling task (Behrens, 1997). It is a good practice