Engaging maintream media for efficient content distribution and creation.

摘要

Artificial Intelligence (AI), when machines act intelligently like human, has emerged in many different fields, including journalism. The interaction between journalism, the Internet and social media has been intensely discussed, helping us understand how journalism can help increase our collective intelligence. In this thesis, we study how AI techniques may contribute to effective information distribution and creation, and network resources utilization. By leveraging mainstream media knowledge, crowd opinions (collective intelligence) and smart algorithms for contextual analysis, we explore a number of novel schemes for efficient content distribution and creation.;We first study trend detection and story development process in the media, and discuss why mainstream media is the tool of our choice. The types of information may vary from textual to visual, among which effective video distribution is one of the most challenging issues. Modern Internet faces new challenges with a growing demand on video; therefore our focus first falls on online video. We propose a mainstream media driven trend detection and proactive caching framework that transits the knowledge of detected trends in news to online video sharing portals, to detect emerging popular videos, and pre-cache them at strategically deployed caching nodes. We explore a combination of topic modeling and frequent pattern mining to design a cross-platform video popularity prediction scheme. We further propose a trend-aware and reputation-based video-ranking algorithm to select correct caching candidates among a large array of redundant content for proactive caching by the Internet Service Providers (ISP). Experimental results show that the proposed proactive caching framework can significantly outperform conventional caching methods that are based on the historical popularity.;Lastly, we discuss the design of a framework that empowers association rule mining by linking semantic entities in the mainstream media to facilitate the creation of an automated news item suggestion system for news generation that could operate as a mainstream media outlet, or serve as a guiding tool for human journalists.