PolyNews

Abstract

The bias in the news media is an inherent flaw of the news production process, spanning news gathering, writing, and editing stages. Producer’s subjective valuation, wittingly or unwittingly, takes place during the daily production process. The resulting bias often causes a sharp increase in political polarization and in the cost of conflict on social issues such as Iraq war. It is very difficult, if not impossible, for readers to have penetrating views on realities against such bias. We present PolyNews, a novel Internet news service framework aiming at mitigating the effect of media bias. PolyNews automatically creates and promptly provides readers with multiple classified viewpoints on a news event of interest. As such, it effectively helps readers understand a fact from a plural of viewpoints and formulate their own, more balanced viewpoints free from specific biased views. The proposed aspect-based clustering is realized through two important clustering steps, i.e., news structure-based clustering and collaborative clustering. We analyze well-known news writing rules and obtain clues on how viewpoint is expressed inside an article to automatically abstract the saliently covered aspect of a news event.