A word embedding technique for sentiment analysis of social media to understand the relationship between Islamophobic incidents and media portrayal of Muslim communities

Abstract

Islamophobia is a sentiment against the Muslim community; recently, atrocities towards Muslim communities witnessed this sentiment globally. This research investigates the correlation between how news stories covered by mainstream news channels impede the hate speech/Islamophobic sentiment. To examine the objective mentioned above, we shortlisted thirteen mainstream news channels and the ten most widely reported Islamophobic incidents across the globe for experimentation. Transcripts of the news stories are scraped along with their comments, likes, dislikes, and recommended videos as the users’ responses. We used a word embedding technique for sentiment analysis, e.g., Islamophobic or not, three textual variables, video titles, video transcripts, and comments. This sentiment analysis helped to compute metric variables. The I-score represents the extent of portrayals of Muslims in a particular news story. The next step is to calculate the canonical correlation between video transcripts and their respective responses, explaining the relationship between news portrayal and hate speech. This study provides empirical evidence of how news stories can promote Islamophobic sentiments and eventually atrocities towards Muslim communities. It also provides the implicit impact of reporting news stories that may impact hate speech and crime against specific communities.

Keywords

• Computer aided design
• Mobile and ubiquitous computing
• Islamophobic
• News stories
• Sentiment analysis
• Natural language processing