Person:

Faris, Robert

In this study, we aim to assess the degree to which English-language Wikipedia is successful in addressing harmful speech with a particular focus on the removal of deleterious content. We have conducted qualitative interviews with Wikipedians and carried out a text analysis using machine learning classifiers trained to identify several variations of problematic speech. Overall, we conclude that Wikipedia is largely successful at identifying and quickly removing a vast majority of harmful content despite the large scale of the project. The evidence suggests that efforts to remove malicious content are faster and more effective on Wikipedia articles compared to removal efforts on article talk and user talk pages.

We analyzed Russian blogs to discover networks of discussion around politics and public affairs. Beginning with an initial set of over five million blogs, we used social network analysis to identify a highly active ‘Discussion Core’ of over 11,000. These were clustered according to long term patterns of citations within posts, and the resulting segmentation characterized through both automated and human content analysis.

Key findings include:

• Unlike their counterparts in the US and elsewhere, Russian bloggers prefer platforms that combine features typical of blogs with features of social network services (SNSs) like Facebook. Russian blogging is dominated by a handful of these “SNS hybrids.”
• While the larger Russian blogosphere is highly divided according to platform, there is a central Discussion Core that contains the majority of political and public affairs discourse. This core is comprised mainly, though not exclusively, of blogs on the LiveJournal platform.