AUTOMATIC STORY SUMMARIZATION FROM CLUSTERED MESSAGES

A set of stories may be related in a set of messages (e.g., news articles, weblog posts, or messages exchanged in a social network). Presented herein are techniques for automatically generating a summary of respective stories that may be used as a headline or title. These techniques involve identifying the entities referenced in each message, clustering the messages based on similarly referenced entities to generate a cluster of messages associated with each story, and identifying facts of the story that appear in many of the messages, which may be used to generate a perspective-independent summary of the story. Additionally, metadata regarding each message may be detected (e.g., the entities involved in each story, a meta-story of the story, and the perspective of the author in relating the story), and may be used to fulfill requests to filter the set of stories and/or messages based on these criteria.