Activision Blizzard has confirmed that more than 20 employees have "exited" the company as part of its efforts to change its internal culture following allegations of fostering a "frat boy" workplace. The video game company has published the letter Executive VP for Corporate Affairs Fran Townsend sent to employees revealing the move, in which she also said that more than 20 other individuals faced different types of disciplinary action. Back in July, the California Department of Fair Employment and Housing filed a lawsuit against the developer for allowing a work environment wherein female employees were allegedly subjected to constant sexual harassment. The agency, which sued the company after a two-year investigation, detailed several of its findings in the lawsuit. It said female employees constantly have to fend off unwanted sexual comments, and that they have to endure being groped by male colleagues. They're also not paid as much as their male counterparts, are typically promoted more slowly and fired more quickly.

At A Glance: Omdena and Spell collaborate with 30 global AI practitioners in a global challenge to harness the power of machine learning to pioneer new approaches to combatting sexual harassment. Sexual harassment is a severe and ongoing problem that plagues communities worldwide today. The issue particularly rampant in India, where thousands of harassment cases are reported each year. Policymakers have been working to create solutions, yet despite efforts to curb offenders and bring justice to victims, there has been little progress in shifting culture on a societal level, perpetuating a society where women must grapple with fear for their safety in public spaces. Recently, Safecity India, an award-winning NGO with the world's most comprehensive database on sexual harassment cases, hosted an Omdena challenge in effort to bring communities together and create an innovative product to fix the problem.

Inspired by the recent social movement of #MeToo, we are building a chatbot to assist survivors of sexual harassment cases (designed for the city of Maastricht but can easily be extended). The motivation behind this work is twofold: properly assist survivors of such events by directing them to appropriate institutions that can offer them help and increase the incident documentation so as to gather more data about harassment cases which are currently under reported. We break down the problem into three data science/machine learning components: harassment type identification (treated as a classification problem), spatio-temporal information extraction (treated as Named Entity Recognition problem) and dialogue with the users (treated as a slot-filling based chatbot). We are able to achieve a success rate of more than 98% for the identification of a harassment-or-not case and around 80% for the specific type harassment identification. Locations and dates are identified with more than 90% accuracy and time occurrences prove more challenging with almost 80%. Finally, initial validation of the chatbot shows great potential for the further development and deployment of such a beneficial for the whole society tool.