Automatic Content Analysis of Media Framing by Text Mining Techniques

Abstract

Political-related news is one of the most popular topics in various media platforms. When news is produced through a process of selection and rephrase by reporters and media firms, reporters' personal political leaning and personal opinions may influence the process, important messages may inevitably loss. In Taiwan, the Parliamentary Library of Legislative Yuan website provides detailed contents about activities happening in the Legislative Yuan, including such contents as transcripts and video recordings of interpellation, conference speech, interim and legislation proposals. Although there is a complete record of information provided online, but the quantity of the legislative documents are far too much for citizens to make sense of. It is imperative that better organized information released to the public would facilitate readers to reduce the cognitive loads in understanding what issues have been discussed by legislators and reported by the media. To minimize the gap between legislative documents and the general public, this study proposes a text mining mechanism to automatically cluster legislative and news documents to identify media frames, and then represents the proportion of each frame corresponding to information sources. The automatic clustering system can determine media frames with the minimum amount of human interference. The results of interviews show that the information system proposed in this study is able to provide political domain experts hard evidences of media framing, and assist the public to discover media framing phenomenon, which are the major contributions of this research.