How News Organizations Paraphrase Their Stories on Social Media? Word Counting and Binomial Regression Approach.

This study aims to investigate news organizations' one potential social media strategy - paraphrasing news. Computational data collection and text analysis techniques in this study allow for a large-scale comparison between social media posts embedded with a link to a news story and the original news stories. To test whether news organizations sentimentalize news on Twitter, I compare valence of news and tweets embedding a link to the original news story. Also, I measured the conditional probability that a word appears on a tweet given that it also appeared on the original news story. I categorized news organizations using a hierarchical clustering algorithm based on the measured paraphrasing strategies. Finally, I suggested a model-based approach that extends the conditional probability measure, which allows for rigorous statistical tests. These analyses are expected to reveal how news organizations frame news on Twitter relative to frames in news stories. [ABSTRACT FROM AUTHOR]