Lost in propagation? Unfolding news cycles from the source

Chenhao Tan, Adrien Friggeri, Lada Adamic.
In Proceedings of the 10th International Conference on Web and Social Media (ICWSM'2016).

Abstract:
The news media play an important role in informing the public on current events. Yet it has been difficult to understand the comprehensiveness of news media coverage on an event and how the reactions that the coverage evokes may diverge, because this requires identifying the origin of an event and tracing the information all the way to individuals who consume the news. In this work, we pinpoint the information source of an event in the form of a press release and investigate how its news cycle unfolds. We follow the news through three layers of propagation: the news articles covering the press release, shares of those articles in social media, and comments on the shares. We find that a news cycle typically lasts two days. Although news media in aggregate cover the information contained in the source, a single news article will typically only provide partial coverage. Sentiment, while dampened in news coverage relative to the source, again rises in social media shares and comments. As the information propagates through the layers, it tends to diverge from the source: while some ideas emphasized in the source fade, others emerge or gain in importance. We also discover how far the news article is from the information source in terms of sentiment or language does not help predict its popularity.

[PDF] [blog on Facebook] [slides]

@inproceedings{tan+etal:16b,
     author = {Chenhao Tan and Adrien Friggeri and Lada Adamic},
     title = {Lost in propagation? Unfolding news cycles from the source},
     year = {2016},
     booktitle = {Proceedings of ICWSM}
}