Abstract:
In recent year, due to the advancement in online social networks, possibility of spreading misinformation increases. Online Social Networks earlier seem to be safer path for sharing information and strengthen the community, but now these platforms become breeding platform for spreading hates, political propaganda and misleading the community. Some folks have toxic behavior who create fruitless arguments and divert the attention of other users from the core objective of a community. With deceptive words, online social network users can get infected by these online misinformation (which can be a fake news also) which create riots and have a tremendous effect on the society already. Through this study, we focus in improving the trustworthiness of information in online world. In this study we have examined 50 YouTube videos which mainly focus on the North-East states and contains the details of incidents happened in these states. These videos come from twenty- three different YouTube channels which we categories in three domain such as Study channels, Influencing channels and News channels through which which we measure which domain prefer by folks to spread toxicity through comments posted on these channels. We leveraged the YouTube Data API to collect the video and comments data from twenty- two channels. We created the word clouds to get the idea about the current status of North-Eastern states. Our analysis suggested that, on average comments on news domain channel contain most negative comments as compare the other domain channels. We further discovered that news domain channels are prefer by the folks to spread toxic behavior. We then use Natural language processing techniques for the sentimental analysis comments which helps us in analyzing which domains have more toxic behavior folks. We further created the network graphs which confirms our desired results.
