The advent of the Internet can be easily heralded as oneof the key events which led to the “Information age” as it is colloquially known. Sharing of thoughts, ideas and opinions reached new heights when people were able to engage in meaningful debates through online forums. However, a darker aspect to this medium – online harassment, has become became rampant in these communities. The Wikipedia usercommunity is no stranger tothis phenomenon.As of January 2019, Wikipedia has 35 million users and on average 250k users register every month. Also, as per the Wikipedia Community Engagement Insights 2018 report - 68% of the respondents reported having experienced harassment at some point in the past and as a result about22% of Wikipedians reported a decrease in their contribution levels. To combat harassment, currently Wikipedia has an organic, human-driven process in place, where cases of abuse reported are evaluated and enacted upon by Wikipedia administrators.Butrelying on human evaluation works in someways but it is not a solution which scales with the growth of Wikipedia, as there were ~170k user blocks in 2018 alone.
Our goal is to develop a data-driven approach in combating cyber harassment that will address a variety of issues that are otherwise faced by the human driven process, from errors and bias in human judgement to efficiently evaluating a larger magnitude of cases. By analyzing user activity in form of editing behavior and discussions, we will be able to predict users who are at risk of getting blocked in the future.
You need this ticket from Eventbrite to sign up:
Applied Machine Learning Conference.
