Shubham Bharti, Arun Kumar Yadav, Mohit Kumar and Divakar Yadav
With the rise of social media platforms, an increasing number of cases of cyberbullying has reemerged. Every day, large number of people, especially teenagers, become the victim…
Abstract
Purpose
With the rise of social media platforms, an increasing number of cases of cyberbullying has reemerged. Every day, large number of people, especially teenagers, become the victim of cyber abuse. A cyberbullied person can have a long-lasting impact on his mind. Due to it, the victim may develop social anxiety, engage in self-harm, go into depression or in the extreme cases, it may lead to suicide. This paper aims to evaluate various techniques to automatically detect cyberbullying from tweets by using machine learning and deep learning approaches.
Design/methodology/approach
The authors applied machine learning algorithms approach and after analyzing the experimental results, the authors postulated that deep learning algorithms perform better for the task. Word-embedding techniques were used for word representation for our model training. Pre-trained embedding GloVe was used to generate word embedding. Different versions of GloVe were used and their performance was compared. Bi-directional long short-term memory (BLSTM) was used for classification.
Findings
The dataset contains 35,787 labeled tweets. The GloVe840 word embedding technique along with BLSTM provided the best results on the dataset with an accuracy, precision and F1 measure of 92.60%, 96.60% and 94.20%, respectively.
Research limitations/implications
If a word is not present in pre-trained embedding (GloVe), it may be given a random vector representation that may not correspond to the actual meaning of the word. It means that if a word is out of vocabulary (OOV) then it may not be represented suitably which can affect the detection of cyberbullying tweets. The problem may be rectified through the use of character level embedding of words.
Practical implications
The findings of the work may inspire entrepreneurs to leverage the proposed approach to build deployable systems to detect cyberbullying in different contexts such as workplace, school, etc and may also draw the attention of lawmakers and policymakers to create systemic tools to tackle the ills of cyberbullying.
Social implications
Cyberbullying, if effectively detected may save the victims from various psychological problems which, in turn, may lead society to a healthier and more productive life.
Originality/value
The proposed method produced results that outperform the state-of-the-art approaches in detecting cyberbullying from tweets. It uses a large dataset, created by intelligently merging two publicly available datasets. Further, a comprehensive evaluation of the proposed methodology has been presented.
Details
Keywords
On 20 March 2020, the four adult convicts of the 2012 Delhi rape case were executed after a long debate regarding the punishment for their crime. The Delhi rape case, unlike…
Abstract
On 20 March 2020, the four adult convicts of the 2012 Delhi rape case were executed after a long debate regarding the punishment for their crime. The Delhi rape case, unlike others, was also given to the fast track court because of the worldwide outrage India received in its aftermath. Otherwise, most rape survivors rarely speak out and if they do, their lives are often endangered and threatened, depending on the severity of the case itself and the perpetrator's rank in the society. Through the analysis of Aniruddha Roy Chowdhury's, 2016 film Pink, and Ajay Bahl's film Section 375 (2019), this chapter explores the different ways in which mainstream Hindi cinema deals with such questions, especially in its depictions of courts. Both these films foreground India's contemporary cultural systems of fear that silence the rape survivors. They also imply that in the court cases, unless the specific court case faces intense global publicity, as was the case of the Delhi gang rape, rape survivors will never want to speak out. Moreover, the rape survivors will also hesitate to file a First Information Report (FIR) – a document that records crimes by the police against their perpetrators – limiting any possibility for justice for them. The laws surrounding rape cases are obscure and complex and finding justice for a rape victim (unless it is on a global level) is not an easy venture in India. At the time of the #metoo movement, the rape laws in India are not designed in such a way to arguably encourage victim-survivors to speak up. Instead, if rape survivors do decide to confront their perpetrators, they not only face ostracisation from society but also the danger of losing loved ones and endanger their lives as well.
Details
Keywords
Mayank Sadana and Dipasha Sharma
This paper aims to analyse how the top over-the-top (OTT) platform is becoming a preferred source of entertainment amongst young consumers over traditional Pay TV service (Cable…
Abstract
Purpose
This paper aims to analyse how the top over-the-top (OTT) platform is becoming a preferred source of entertainment amongst young consumers over traditional Pay TV service (Cable TV/DTH) in India and what factors play a vital role in such preferences along with gamification of content. The study follows the theoretical framework of use and gratifications theory and Niche analysis.
Design/methodology/approach
The study establishes a conceptual framework of understanding the preference of consumers, which triggers the shift from old media to new. This research develops an approach to understanding the relevant implications in responses of consumers through a structured online survey conducted amongst different age groups by applying exploratory and confirmatory factor analysis. To further comprehend the relations between measured variables and constructs, the statistical technique is incorporated, i.e. logistic regression.
Findings
Empirical results and discussion insinuated the five factors which affect consumers’ choices concerning entertainment i.e. content and viewing behaviour, expenses incurred on services, shifts influenced by offerings/incentives, convenience and telecom. Logistic regression validated the strength of these factors which made content and viewing behaviour, expenses incurred on services and convenience the three most important factors.
Research limitations/implications
This study analyses the driving factors that are revolutionising the entertainment industry and can be applied in designing a comfortable and engaging experience for a consumer in the future.
Originality/value
This research is original in nature and the findings of this study are valuable for online streaming services, video-on-demand services, Cable TV operators and entertainment content producers.