Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Division
Browse By Session Type
Search Tips
Personal Schedule
Sign In
This study uses computational methods to analyze differences in user comments to news articles posted on three different platforms: a newspaper’s website, the comments posted on a news website through Facebook Plugin, and comments on the newspaper’s Facebook page. The cross-platform approach is aided by custom-built data mining tools designed for extracting comments to the same article from the three platforms, while automatically computing parameters such as the comments’ average count and length. In addition, topic modeling is used to characterize comments across platforms as well as journalistic genres (following Tuchman’s distinction between hard and soft news). Our findings suggest that although there are more comments to news articles posted on a newspaper’s Facebook page than on its website, these are relatively short and emotionally intense, which might indicate a bias in the discussion of news on these two platforms.