Designing an Algorithm-Driven Text Generation System for Personalized and Interactive News Reading

摘要

Algorithms are playing an increasingly important role in the production of news content as their computation capacity in manipulating large-scale data continues to grow. In this article, we present Personalized and Interactive News Generation System (PINGS), an algorithm-driven news generation system that is designed to provide personalized and interactive news for sports. We designed PINGS to generate baseball news based on the statistical importance of data and the direct manipulation of user interface components that alter the underlying algorithmic computation. We discuss the base-level algorithm framework for automated news content generation and describe the architecture of the system in terms of how it is designed to support the generation of personalized news stories. An evaluation revealed that the algorithm is capable of generating news stories that are significantly more interesting and pleasant to read than traditional baseball news articles.