TL;DR: “Precision” is a measure of the accuracy of a detection system. Improving precision is to reduce your false positive rate. “Recall” is a measure of the coverage of a detection system. Improving recall is to reduce your false negative rate.
Prior research on content moderators has failed to explore moderators' initial reactions to content from the start of employment through tenure as the subjection to material and habituation increases. This qualitative study takes an in-depth look at moderators' experiences from recruiting, through training, and production to better understand the content moderators' startle response and factors that enable startle habituation.
An introduction to the ways consumer internet services are abused to cause real human harm and the potential operational, product and engineering responses. Students will learn about spam, fraud, account takeovers, the use of social media by terrorists, misinformation, child exploitation, harassment, bullying and self-harm. This will include studying both the technical and sociological roots of these harms and the ways various online providers have responded. Our goal is to provide students with an understanding of how the technologies they may build have been abused in the past and how they might spot future abuses earlier. The class will be taught by a long-time practitioner and supplemented by guest lecturers from local companies.
