Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 2.541

On the dynamics of user engagement in news comment media

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract Many news outlets allow users to contribute comments on topics about daily world events. News articles are the seeds that spring users' interest to contribute content, that is, comments. A news outlet may allow users to contribute comments on all their articles or a selected number of them. The topic of an article may lead to an apathetic user commenting activity (several tens of comments) or to a spontaneous fervent one (several thousands of comments). This environment creates a social dynamic that is little studied. The social dynamics around articles have the potential to reveal interesting facets of the user population at a news outlet. In this paper, we report the salient findings about these social media from 15 months worth of data collected from 17 news outlets comprising of over 38,000 news articles and about 21 million user comments. Analysis of the data reveals interesting insights such as there is an uneven relationship between news outlets and their user populations across outlets. Such observations and others have not been revealed, to our knowledge. We believe our analysis in this paper can contribute to news predictive analytics (e.g., user reaction to a news article or predicting the volume of comments posted to an article). This article is categorized under: Internet > Society and Culture Ensemble Methods > Web Mining Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction
The hierarchical diagram of the social media ecosystem at a news outlet
[ Normal View | Magnified View ]
Quantifying breadth and heterogeneity of user populations at news outlets in news stories. (a) User interest heterogeneity evaluated on discrete representation and (b) user interest breadth evaluated on binary representation
[ Normal View | Magnified View ]
Cumulative plot of averaged breadths of user interest (number of distinct stories). Users are ranked by their breadths of interest from large to small
[ Normal View | Magnified View ]
Cumulative comment growth over time for story. (a) Apple, (b) Angela Merkel, and (c) Fort McMurray
[ Normal View | Magnified View ]
User engagement versus story popularity. (a) Appearance in GNews and (b) Disappearance in GNews
[ Normal View | Magnified View ]
Cumulative comment volume over time
[ Normal View | Magnified View ]
User stickiness. (a) Monthly user retention rates about “Donald Trump” related articles in 2016 on Wall Street Journal. (b) User Stickiness: distribution of monthly user retention rate about “Donald Trump” related articles in 2016 across five major news outlets
[ Normal View | Magnified View ]
Comment volume per hour at Daily Mail, focusing on the users from United Kingdom. The time of comment is displayed by the users time zone
[ Normal View | Magnified View ]
The volume of user comments by time at each outlet. WSP, Washington Post; DM, Daily Mail; WSJ, Wall Street Journal; Gd, The Guardian; NYT, New York Times; MW, Market Watch. (a) Comment volume in each day of a week. (b) Comment volume in each time span of a day
[ Normal View | Magnified View ]
Distribution of the duration of user commenting activity at each outlet. The duration is defined as the time difference between the last and first comment in an article
[ Normal View | Magnified View ]
Distribution of user reaction at Fox News. User reaction is defined as the time difference between the first comment and the article publication time
[ Normal View | Magnified View ]
Interplay between news outlets and users. (a) Daily Mail, (b) Fox News, (c) Washington Post, (d) The Guardian, (e) New York Times, and (f) Wall Street Journal
[ Normal View | Magnified View ]
The modeling of interplay between outlets and users
[ Normal View | Magnified View ]
Proportion of each outlet for top 10 distinct stories based on total article volume
[ Normal View | Magnified View ]
Comment volume from user population. Users are ranked based on the number of comments they post
[ Normal View | Magnified View ]

Browse by Topic

Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction
Algorithmic Development > Web Mining

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts