• PDF / 262,329 Bytes
• 8 Pages / 439.37 x 666.142 pts Page_size
• 106 Downloads / 366 Views

DOWNLOAD

REPORT

---

Abstract The aim and objective of this research are to create a model to measure the hate speech and to measure the contents of hate speech. The descriptive analysis method of data science was used to describe and summarize raw data from a dataset. We used Twitter as the social networking Web site for this research to analyze and measure the hate speech and its classifications. A dataset from kaggle datasets was applied for this research. To produce statistical results, we used monkey learn machine learning libraries which are incorporated with Python program to design and develop a model to classify and measure hate speech and its types that could be trained and tested using sentiment analysis. Researchers have found that the majority of the tweets are based on racist and ethnicity, sex and religion-based hate speech are also widely available. Keywords Machine learning · Hate speech · Social media and Twitter

1 Introduction The rapid growth of social networking sites or social media such as Facebook, Instagram, Twitter, and other online social forums has transformed the pattern of communication and content publishing but is also increasingly misused for the circulation of hate speech and the organization of hate-based activities [1]. The term “hate speech” was formally defined as “any communication that disparages a person or a group based on some characteristics (to be referred to as types of hate or hate classes) F. H. A. Shibly (B) · U. Sharma Assam Don Bosco University, Guwahati, India e-mail: [email protected] U. Sharma e-mail: [email protected] F. H. A. Shibly · H. M. M. Naleer South Eastern University of Sri Lanka, Oluvil, Sri Lanka e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2021 D. Gupta et al. (eds.), International Conference on Innovative Computing and Communications, Advances in Intelligent Systems and Computing 1165, https://doi.org/10.1007/978-981-15-5113-0_54

671

672

F. H. A. Shibly et al.

such as race, color, ethnicity, gender, sexual orientation, nationality, race, or other characteristics” [2]. Social media is a widely used technology among all the people today. There is an environment that anyone can make any comment at any time on social media. Though there are advantages, disadvantages also take place. Indeed, a survey is being carried out to verify the differences between hate speech and independent speech. The difference between the two is not clear for social media users. It is found that hate speech is not controlled on common platforms and it is freely made. Social media does not have any distinction between hate speech and independent speech. Although several reviews and attempts have taken place on this, nothing has been achieved, though every social media has taken some steps to stop hate speech which is extremely difficult to control hate speech. Several years ago, social and scientific reviews on hate speech were conducted. But no correct detections or quick solutions were found. Hence, it is imperative to identify it through a technological method.