Analyzing the bias in public opinion and media reports for events in different geographical areas

Abstract

News media is considered as voice of public which represent opinion of people. Sometimes it is observed that news media is biased in case of some certain topic. Now a days people use social media as a major source for presenting their opinion. There is difference of opinion presented on social media and national news media. There is a third source which is responsible for forming opinion of other countries about certain event that is international news media. In this research we have used these three sources to detect biasness of opinion. For public opinion we have used twitter. Twitter is widely used by public for the expression of sentiment. Tweets of Pakistani region are collected to detect opinion of Pakistani public. For national news media two major sources are used. These sources are The nation and Dawn. These are most popular English newspaper in the country. For the collection of international news Reuters, and Aljazeera are used. After the collection of dataset topical keyphrases are extracted and sentiment analysis is performed. Then news articles and tweets sentiments are compared in order to classify the news article as biased or unbiased. Major finding of this research is that is case of politics related topics national as well as international news media is totally biased. In case of general issues of society media present true sentiment of public. Web application biasness detector is developed for this research. Results produced by this application are evaluated. Evaluation is done manually as there is no existing application with which we could compare result.