Published inSentropySentropy x Discord: A Safer TomorrowFor the Sentropy team, today is a big day. For the Sentropy mission, today is a monumental day. Three years after starting this company…Jul 13, 20214Jul 13, 20214
Published inSentropyHow to build a content moderation systemAnyone who is managing a platform with user-generated content knows the risks. Insults, spam, hate speech, profanity, and other types of…May 7, 2021May 7, 2021
Published inSentropyMeet Cindy, a machine learning engineer at SentropyMeet Cindy Wang, a machine learning engineer at Sentropy. Cindy talks about her passion for using machine learning to detect hate speech…Mar 19, 2021Mar 19, 2021
Published inSentropyMeet Dev Bala, Sentropy’s Chief Product OfficerWith nearly 20 years of experience in product management, Dev joined Sentropy after leading product teams at Microsoft, Google, and…Mar 17, 2021Mar 17, 2021
Published inSentropyBuilding content moderation at scale with human-centered MLWhy automating abuse detection is hard, and how we bring together experts and AI to tackle it.Mar 12, 2021Mar 12, 2021
Published inSentropyFighting Abuse Online: Recommendations for the Biden-Harris AdministrationThe world is a very different place than it was just 20 years ago. The internet now touches nearly every part of our lives, and, today…Mar 3, 2021Mar 3, 2021
Published inSentropyContent moderation for your platform: Should you build or buy?If you’re looking to detect and defend against abuse on your platform, consider the ins and outs of developing internally vs. purchasing.Feb 15, 2021Feb 15, 2021
Published inSentropyProtecting the real world: Capitol riots & content moderationIt has become impossible to deny, after the events of 2020 and the Capitol riots, that something is intrinsically flawed with how we…Jan 15, 2021Jan 15, 2021
Published inSentropyWhy is content moderation so hard?Abusive content harms communities and brings about serious real-world consequences. Here’s why it isn’t yet under control.Oct 1, 2020Oct 1, 2020
Published inSentropyToken Bias in Subword-Based Hate Speech ClassifiersIn this post, we show that bias caused by overrepresentation exists not only on the word level, but also on the subword level, which can..Sep 16, 2020Sep 16, 2020