Skip to main content
. Author manuscript; available in PMC: 2017 Sep 27.
Published in final edited form as: Proc Int World Wide Web Conf. 2017 Apr;2017:1073–1081. doi: 10.1145/3041021.3055134

Figure 1.

Figure 1

An example debate in thread as the input of our model. Green and blue posts were published by two users engaged in the debate with opposing opinions respectively. Grey posts are not engaged in the debate, but provide as context. User names are removed from the text and replaced by X, Y, and Z, from which it could be seen that debate detection is highly context-dependent.

HHS Vulnerability Disclosure