This paper presents a study of the life cycle of news articles posted online. We describe the interplay between website visitation patterns and social media reactions to news content. We show that we can use this hybrid observation method to characterize distinct classes of articles. We also find that social media reactions can help predict future visitation patterns early and accurately.We validate our methods using qualitative analysis as well as quantitative analysis on data from a large international news network, for a set of articles generating more than 3,000,000 visits and 200,000 social media reactions. We show that it is possible to model accurately the overall traffic articles will ultimately receive by observing the first ten to twenty minutes of social media reactions. Achieving the same prediction accuracy with visits alone would require to wait for three hours of data. We also describe significant improvements on the accuracy of the early prediction of shelf-life for news stories.
One of the biggest news stories of 2012, the killing of Trayvon Martin, nearly disappeared from public view, initially receiving only cursory local news coverage. But the story gained attention and controversy over Martin's death dominated headlines, airwaves, and Twitter for months, thanks to a savvy publicist working on behalf of the victim's parents and a series of campaigns off-line and online. Using the theories of networked gatekeeping and networked framing, we map out the vast media ecosystem using quantitative data about the content generated around the Trayvon Martin story in both off-line and online media, as well as measures of engagement with the story, to trace the interrelations among mainstream media, nonprofessional and social media, and their audiences. We consider the attention and link economies among the collected media sources in order to understand who was influential when, finding that broadcast media is still important as an amplifier and gatekeeper, but that it is susceptible to media activists working through participatory or nonprofessional media to co-create the news and influence the framing of major controversies. Our findings have implications for social change organizations that seek to harness advocacy campaigns to news stories, and for scholars studying media ecology and the networked public sphere. Contents Background Context for the study Methods and data Chronological analysis Statistical comparison of media attention measures Bitly data and the role of race-specific media Conclusions Future work Background On 19 February 2012, 17-year-old black male Trayvon Martin and his father traveled to Sanford, Florida to visit his father's fiancée in the Retreat at Twin Lakes housing development. The gated community had recently experienced a string of burglaries. During the halftime of the NBA All-Star Game on 26 February, Martin walked to a nearby convenience store to get an iced tea and a bag of Skittles for himself and his stepbrother-to-be. It rained that evening, and Martin wore a hooded sweatshirt. Martin caught the eye of Neighborhood Watch volunteer George Zimmerman, a 28-year-old Hispanic man, as he drove his car on an errand. Zimmerman had previously reported suspicious individuals to the Sanford Police Department on five occasions, including an incident on 2 February 2012, when he reported two young black men, who went on to burglarize a house four days later. Zimmerman called the Sanford Police Department to report Martin. As Zimmerman called the police, Martin was on the phone with his girlfriend, and told her that someone was following him. While Zimmerman spoke to the police dispatcher, Martin fled, and the dispatcher asked him not to pursue him. Zimmerman pursued Martin anyway. An altercation occurred between the two, which Zimmerman has claimed was initiated by Martin. Zimmerman sustained injuries to his nose and the back of his head. A witness called 911; cries for help and a gunshot can be heard on the call audio. Sanford Police officers arrived, followed by Sanford ...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.