Search

Content is the new oil. Users consume billions of terabytes a day while surfing on news sites or blogs, posting on social media sites, and sending chat messages around the globe. While content is heterogeneous, the dominant form of web content is text. There are situations where more diversity needs to be introduced into text content, for example, to reuse it on websites or to allow a chatbot to base its models on the information conveyed rather than of the language used. In order to achieve this, paraphrasing techniques have been developed: One example is Text spinning, a technique that automatically paraphrases text while leaving the intent intact. This makes it easier to reuse content, or to change the language generated by the bot more human. One method for modifying texts is a combination of translation and back-translation. This paper presents NATTS, a naive approach that uses transformer-based translation models to create diversified text, combining translation steps in one model. An advantage of this approach is that it can be fine-tuned and handle technical language. [ABSTRACT FROM AUTHOR]

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]