The internet is a powerful tool for connecting people, but it also has a dark side. Online hate speech has been on the rise and its impact is felt offline in the form of increased hate crimes and (verbal) assaults or insults.
At Tilt, we believe that the world should be a safe and inclusive place for everyone, regardless of race, religion, gender, or sexual orientation. That’s why we’re on a mission to make the internet a safer place by combating and detecting online hate speech.
Definition of Hate Speech Following Röttger et al. (2021b): we define hate speech as abuse that is targeted at a protected group or at its members for being a part of that group. Protected groups are groups based on age, disability, gender identity, race, national or ethnic origins, religion, sex or sexual orientation, which broadly reflects Western legal consensus, particularly the US 1964 Civil Rights Act, the UK’s 2010 Equality Act and the EU’s Charter of Fundamental Rights. Based on these definitions, we approach hate speech detection as the binary classification of content as either hateful or non-hateful
Monitoring the vast amounts of online content is a daunting task. We also understand that hate speech isn’t just offensive, it’s dangerous because it leads to harmful offline consequences. Therefore we need a rapid and professional approach to combat it as current methods are time-consuming and ineffective.
With Tilt’s Hate Speech Detection solution, you can take action against hate speech before it has a chance to escalate into serious offline incidents. Our online platform offers near real-time monitoring to detect hate speech, using data analysis and machine learning. By speeding up and automating the process, we enable you to focus on taking action against harmful content and make a significant difference.
Tracking online indicators of racism, anti-Semitism, Islamophobia, misogyny, nationalism, or extremism linked to offline events.
Protecting free press and democracy by monitoring online hate speech targeting journalists and politicians.
Detecting hate speech and mobilization language to prevent escalating riots.
Set up a thorough and customised investigation
Automate detection of hate speech
Filter and rank hateful, toxic and violent content
Visualise Networks, Patterns and Relationships
Analyse Narratives over time
We are a close-knit team that is passionate about making a difference. We’ve got the expertise, the technology, and the drive to tackle online hate head-on. Using Tilt’s Hate Speech Detection, we’re delivering real results for our clients. By providing hate speech detection in social media, we’re reducing hate-related crimes and promoting inclusiveness and safety online.
So if you want to make a positive change, join us on our mission. With Tilt’s Hate Speech Detection, you are one step closer to stopping hate speech in its tracks.
"*" indicates required fields