Hate and Aggression Detection in Social Media Over Hindi English Language

Hate and Aggression Detection in Social Media Over Hindi English Language

Kapil Pareek, Arjun Choudhary, Ashish Tripathi, K. K. Mishra, Namita Mittal
DOI: 10.4018/IJSSCI.300357
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In today’s time, everyone is familiar with social media platforms. It is quite helpful in connecting people. It has many advantages and some disadvantages too. Currently, in social media, hate and aggression have become a huge problem. On these platforms, many people make inflammatory posts targeting any person or society by using code mixed language, due to which many problems arise in the society. At the current time, much research work is being done on English language-related social media posts. The authors have focused on code mixed language. Authors have also tried to focus on sentences that do not use abusive words but contain hatred-related remarks. In this research, authors have used Natural Language Processing (NLP). Authors have applied Fasttext word embedding to the dataset. Fasttext is a technique of NLP. Deep learning (DL) classification algorithms were applied thereafter. In this research, two classifications have been used i.e. Convolutional Neural Network (CNN) and Bidirectional LSTM (Bi-LSTM).
Article Preview
Top

Introduction

Until a few years ago, the internet was used to read or disseminate information only. Later, along with the development of web technology, social media platforms were also developed which increased the popularity of the internet. There has been an exponential development of web technology in the last decade, as well as the number of users on social media has also increased manifold. These platforms have proved to be a very advanced and effective medium to spread anyone’s point of association with people, society, or any cult or philosophy. Here people make contact with their relatives, friends and new people, they share things, share ideas, photo videos and other issues.

These platforms also have a dark side. On these platforms, anyone can create a new post against any person or comment on any post by giving misleading or wrong information. This is an easy task to do, but the results are really fatal. The freedom of thought on these platforms, sometimes also poses a risk. Many people do not understand their responsibilities regarding it and post it carelessly. These loopholes promote cyberbullying (Smit, D, 2015). Bully people use social media as a weapon and to increase violence in society and spread hatred. These platforms are really good for them as they need not be physically present, as well as they can hide their identity or create a false identity. It is a little bit difficult to catch people like these due to all these reasons.

Trolling is defined by (Fichman et.al, 2016) as disturbing behaviour on the internet among users having no relationship in real life. It can be towards an individual or a social group relating to politics or a corporate entity. The case of hate speech and violent communication conducted over the internet can be referred to as cyber hate (Miro and Rodriguez, 2016). In hate speech, one person or group targets another group or individuals and makes violent posts about their religion, location, or physical appearance with the wrong intention (Areej and Hmood, 2019). In aggression posts, a user is aggressive about any matter. This type of person flares up very quickly with any post and with an aggressive attitude starts targeting any specific person and posts violently in the end. In hate speech, a bully intentionally targets someone’s gender, religion, caste. Similarly, like aggression, bully is aimed against an individual or group with aggressive vocals, fostering personal enmity.

Figure 1.

Hate and aggression examples on various social media platform

IJSSCI.300357.f01

Figure 1 shows certain examples of social media platform’s hate speech and aggression. Bullying, trolling, hate speech and aggression all these are usually the triggers for the onset of cybercrime, which has very serious effects on the victim’s life such as suicide, impact on self-confidence, social attitude of the victim, reputation, mental health, and severe depression.

A recent survey has revealed that after the COVID19 pandemic, there has been a 900% increase in the use of hate speech against China on social media, as well as the promotion of hate speech sites against people in Asia on Twitter (Bhardwaj et.al, 2020). A survey considered by feminism in India has noted that online abuse has been faced by more than 50% of females in major cities of India (Kumari, K. and Singh, J.P, 2019). As we know for aggression on social media only resource needed is the internet, which makes it easier and it can be done from anywhere and anytime. This type of hatred or cyberbullying is found to be a new psychological type of disease. One study conducted by a national anti-bullying charity titled “Ditch the Label” in 2013, has shown that two out of three 13-22 years old who were surveyed have been victims of cyberbullying (Zhao et al., 2016). The government of India is also dealing with this problem and wants to bring down tough laws. The government also wants tools or techniques that can identify and remove hate speech (Kamble, S. and Joshi, 2018).

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing