Assistant Professor, @Stanford MS&E. Social networks, social and behavioral data. Occasionally disappear into the mountains.
Apr 29, 2023 • 10 tweets • 2 min read
Great thread, paper here: arxiv.org/abs/2301.07015 A good time to tell a short story from when I worked on fake account detection a bit at Facebook in 2010. 🧵 1/
In 2010 I was visiting FB data science as a PhD intern, to study FB's growth. Four weeks in, I stumbled upon a backdoor that had been used to generate unknown millions of spam accounts. It was one week before FB was set to announce reaching 500m users (with a big party)… 2/
Jan 4, 2022 • 9 tweets • 2 min read
I'm teaching "Networks" at Stanford again this quarter, my 7th run of the course with 100+ students, following the excellent Easley & Kleinberg textbook (and mega-class at Cornell!). Always a thrill. If you teach a related class, here's an awesome lecture trick… 🧵 1/
When introducing connected components, giant components (informal only!), and shortest path distance, E&K Chapter 2 has great pedagogy, using breadth-first-search (BFS) as a basic and natural algorithmic device for finding shortest paths: cs.cornell.edu/home/kleinber/… 2/
Nov 10, 2021 • 19 tweets • 6 min read
I wanted to chime in to specific "true vs. false news" discussions that are happening on twitter this week. In this thread: (i) "true vs. false news" != "true vs false fact-checked rumors" and what that means, (ii) "do false rumors go deeper than true?" (yes), and more.👇🧵 /1
What does Vosoughi et al (2018) teach us about "true vs false news"? As @dkroy pointed out in 2018, they studied fact-checked content. It's an excellent study of that sample frame, but insights must be understood in terms of that sample frame. /2
"An Experimental Study of Structural Diversity in Social Networks," new paper with @jessicatysu, @krishna_kamath, @aneeshs, and @5harad, to appear at ICWSM 2020: arxiv.org/abs/1909.03543 Several years in the making, I'm really excited to share this work! 1/n
In adoption decisions based on social referrals, what about graph structure? Classic modeling of such decisions study "influence response functions", adoption as a function of # of adopted friends, see e.g. this classic by @duncanjwatts/@peterdodds: jstor.org/stable/10.1086… 2/n
Jan 27, 2018 • 12 tweets • 5 min read
Terrific reporting by @NYTimes team. I stumbled upon these "createtime fingerprints" independently in August 2017, and have been thinking a lot about them since, so thought I'd share some thoughts. [thread] 1/n
