In this paper, we present our efforts to protect various social media entities at Facebook from people who try to abuse our platform. We present a novel Temporal Interaction EmbeddingS (TIES) model that is designed to capture rogue social interactions and flag them for further suitable actions. TIES is a supervised, deep learning, production ready model at Facebook-scale networks.
In this paper, we present CLARA (Confidence of Labels and Raters), a system developed and deployed at Facebook for aggregating reviewer decisions and estimating their uncertainty. We perform extensive validations and describe the deployment of CLARA for measuring the base rate of policy violations, quantifying reviewers’ performance, and improving their efficiency.
We study a problem arising in statistical analysis called the minimum bottleneck generalized matching problem that involves breaking up a population into blocks in order to carry out generalizable statistical analyses of randomized experiments.
As we increasingly integrate technology into our lives, we need a better framework for understanding social interactions across the communication landscape. Utilizing survey data in which more than 4,600 people across the United States, India, and Japan described a recent social interaction, this article qualitatively and quantitatively explores what makes an interaction meaningful.
To better test the potential causal pathways between trust and behaviors or group properties, we paired a two-wave longitudinal survey of 2358 participants in Facebook Groups with logged activity on Facebook. Using latent change score modeling, we examined how trust may predict changes in behavior or group properties and how behaviors and group properties may predict changes in trust.
Basic block reordering is an important step for profile-guided binary optimization. The state-of-the-art for basic block reordering is to maximize the number of fall-through branches. However, we demonstrate that such orderings may impose suboptimal performance on instruction and I-TLB caches. We propose a new algorithm that relies on a model combining the effects of fall-through and caching behavior.
People compare themselves to one another both offline and online. The specific online activities that worsen social comparison are partly understood, though much existing research relies on people recalling their own online activities post hoc and is situated in only a few countries. To better understand social comparison worldwide and the range of associated behaviors on social media, a survey of 38,000 people from 18 countries was paired with logged activity on Facebook for the prior month.
This paper compares data from ten self-reported Facebook use survey measures deployed in 15 countries (N = 49,934) against data from Facebook’s server logs to describe factors associated with error in commonly used survey items from the literature.