This looks interesting I'm going to see if I cannot find a way to do this. (I will assign myself if I find out how.)

One possible approach is detecting references which are controversial (by detecting removal or edit war patterns, maybe appearance in fact check databases, manual blacklists) and then flagging sentences which are supported by such references.

Relevant:

Ciampaglia, G. L., Shiralkar, P., Rocha, L. M., Bollen, J., Menczer, F., & Flammini, A. (2015). Computational fact checking from knowledge networks. PloS one, 10(6), e0128193. http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0128193

Ping @GLCiampaglia

cc @srijan @Hjfocs @Tarrow @Cervisiarius

Thanks @Halfak, very interesting initiative, happy to brainstorm!

@diego can you do a pass over this task and let me know how much similarity do you see between the current description of the task and the work you're doing at https://meta.wikimedia.org/wiki/Research:Discovering_content_inconsistencies_between_Wikidata_and_Wikipedia ? Given that the current task is not assigned to anyone, I'd encourage you to consider merging tasks if there is a close alignment.

@leila I see some overlap although this task seems to be broader than the one I'm working on. Given that I don't see much documentation nor code about this task, I prefer to not take responsibility on this.

@diego ok. we shall leave it like this then. thanks for checking.