WTF: the who to follow service at Twitter

By Pankaj Gupta, Ashish Goel, Jimmy J. Lin, Aneesh Sharma, Dong Wang, Reza Bosagh Zadeh. 2013

528 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

Data Encoding for Byzantine-Resilient Distributed Optimization (2019, methodology): “…the largest eigenvalue of a diagonalizable matrix, which is used in Google’s PageRank algorithm [ISW06], Twitter’s recommendation system [GGL + 13], etc.; (ii) iterative methods for solving sparse linear systems [Saa03]; (iii) many graph algorithms, where the graph is represented by a ﬁxed…”
Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms (2015, neutral): “For most problems, this update step is easy to compute, and perhaps because of this SGD is a ubiquitous algorithm with a wide range of applications in machine learning [1], including neural network backpropagation [2, 3, 13], recommendation systems [8, 19], and optimization [20].”
Multistakeholder recommendation: Survey and research directions (2020, background): “ers [66]. This relationship type is often associated with a \follow" recommendation in asymmetric networks, where a user can connect to another party without their need to approve or reciprocate [52]. With reciprocity removed, this type of recommendation more closely resembles the standard hC p”
Personalized Search (2015, background): “However, there are also recommendation systems for such as restaurants [40], financial services [14] and Twitter followers [18].”
FAST-PPR: scaling personalized pagerank estimation for large graphs (2014, background): “Pokec and Twitter are both social networks in which edges are directed.”
The Effect of Recommendations on Network Structure (2016, methodology): “Focusing on Twitter, we analyze abrupt changes in the network following the July 2010 introduction of its “Who To Follow” feature [15], one of the largest and most active network recommendation systems.”
A Graph-Based Push Service Platform (2016, methodology): “There are many variants of PageRank, such as sensitive PageRank [6], xRank [7], and WTF [4].”
CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation (2018, methodology): “From an application perspective, our work is also highly related to ‘Peo-ple you might know’ or ‘who to follow’ (WTF) services on RSNs (Gupta et al. 2013) albeit taking a romantic twist.”
GraphJet: Real-Time Content Recommendations at Twitter (2016, methodology): “Graph recommendations began at Twitter in spring 2010 with the Wtf (“Who to Follow”) project [17], which focused on providing user recommendations.”
Scalable Temporal Latent Space Inference for Link Prediction in Dynamic Social Networks (2014, background): “tions in dynamic networks. In addition to purely academic interest, scalable link prediction methods have many important commercial applications, e.g., suggesting friends in an online social networks [11], or potential hires in a professional network such as LinkedIn. The focus of this work is on pr”
Style in the long tail: discovering unique interests with latent variable models in large scale social E-commerce (2014, unknown): “’s description of Twitter’s “Who to Follow” System [9].”
Information network or social network?: the structure of the twitter follow graph (2014, background): “Many algorithms, particularly edge prediction algorithms, use this set of vertices as the starting point for predicting the formation of new edges [6].”
"On the internet, nobody knows you're a dog": a twitter case study of anonymity in social networks (2014, background): “Studies have also been undertaken to improve usability of Twitter, such as developing a user recommendation service [18].”
One Trillion Edges: Graph Processing at Facebook-Scale (2015, methodology): “Single machine graph computing implementations such as Cassovary [23] are used at Twitter.”