The online mass media plays a critical role in influencing the public opinion about controversial political events. Bias in press reports and articles to some ideological or political sides is common and opposites the neutrality nature of press and media. Bias can take different aspects and ways. One of the main aspects of press bias is using mislead terms and vocabularies. In summer 2014, Western media, news and press agencies covered Israeli war on Gaza. In general, Palestinian people complain that there is a notable bias in western media with the Israeli story and opinion and vice versa. In this research paper we report a text mining experimental study, that's have conducted on western media analysis to identify patterns in the press orientation and further in the media bias towards side to another. We have followed the text mining techniques and machine learning in an effort to detect the bias in news agencies. We have crawled news articles form seven major outlets in the western media. Then we have made preprocessing to convert them into useful structured form, building sentiment classifiers that be able to predict articles bias. In addition, we have compared three of supervised machine learning algorithms used in sentiment classification associated with different number of grams, where we have found that SVM with bio-gram gave the better outperformed outputs, with performance metrics are 91.76% accuracy, 88.33% recall and f-measure 91.46%.
