WTF: the who to follow service at Twitter

@inproceedings{Gupta2013WTFTW,
  title={WTF: the who to follow service at Twitter},
  author={Pankaj Gupta and Ashish Goel and Jimmy J. Lin and Aneesh Sharma and Dong Wang and Reza Bosagh Zadeh},
  booktitle={WWW '13},
  year={2013}
}
WTF ("Who to Follow") is Twitter's user recommendation service, which is responsible for creating millions of connections daily between users based on shared interests, common connections, and other related factors. This paper provides an architectural overview and shares lessons we learned in building and running the service over the past few years. Particularly noteworthy was our design decision to process the entire Twitter graph in memory on a single server, which significantly reduced… Expand
View on ACM
stanford.edu
423 Citations
Highly Influential Citations
42
Background Citations
195
Methods Citations
82
Results Citations
4

423 Citations

Citation Type

Citation Type

Recommendation of microblog users based on hierarchical interest profiles
TLDR
This paper proposes to accomplish the recommendation task in two steps, and casts both problems of user classification and recommendation as one of itemset mining, where items are either users’ authoritative friends or semantic categories associated to friends, extracted from WiBi, the Wikipedia Bitaxonomy. Expand
SimClusters: Community-Based Representations for Heterogeneous Recommendations at Twitter
TLDR
This paper presents SimClusters, a general-purpose representation layer based on overlapping communities into which users as well as heterogeneous content can be captured as sparse, interpretable vectors to support a multitude of recommendation tasks. Expand
WTF, GPU! computing twitter's who-to-follow on the GPU
TLDR
This paper implements Twitter's WTF ("Who to Follow") recommendation system on a single GPU, showing promising results on moderate-sized social graphs and proposing possible solutions to apply the system to follow graphs of larger sizes that do not fit into the on-board memory of a singleGPU. Expand
GraphJet: Real-Time Content Recommendations at Twitter
TLDR
This paper presents GraphJet, an in-memory graph processing engine that maintains a real-time bipartite interaction graph between users and tweets and organizes the interaction graph into temporally-partitioned index segments that hold adjacency lists. Expand
Searching for people to follow in social networks
TLDR
This paper defines the problem of SPTF and proposes an approach to give users tags and then deliver a ranked list of valuable accounts for them to follow, and proposes two algorithms to rank relevant accounts: the first mines the forwarded relationship, and the second incorporates the following relationship into PageRank. Expand
Semantic Enabled Recommender System for Micro-Blog Users
TLDR
A method for analysis of Twitter users supported by a hierarchical representation of their interests, which is called a Twixonomy, and shows that semantic categories allow for very fine-grained population studies, and make it possible to recommend not only whom to follow, but also topics of interest, users interested in the same topic, and more. Expand
A semantic followee recommender in Twitter using Topicmodel and Kalman filter
TLDR
Preliminary analysis show that the model can effectively recommend useful followees in Twitter, and a case study is conducted to evaluate the efficacy of the model to recommend followingees in six predefined classes: politics, sports, business, entertainment, science, and travel. Expand
Twitter-user recommender system using tweets: A content-based approach
  • R. Nidhi, B. Annappa
  • Computer Science
  • 2017 International Conference on Computational Intelligence in Data Science(ICCIDS)
  • 2017
With the advent of the internet into our everyday lives, online social networks such as Facebook and Twitter have taken up a major role in networking, information deployment and entertainment. As of… Expand
Twitter User Recommendation for Gaining Followers
TLDR
A recommendation system that leverages features ranging from basic social media attributes to specialized, domain-relevant user profile attributes predicted from data using machine learning techniques is proposed and a preliminary analysis of its performance in gathering new followers in a Twitter scenario where the account manager follows recommended users to trigger their follow-back. Expand
From user graph to Topics Graph: Towards twitter followee recommendation based on knowledge graphs
  • Danae Pla Karidi
  • Computer Science
  • 2016 IEEE 32nd International Conference on Data Engineering Workshops (ICDEW)
  • 2016
TLDR
This work proposes a followee recommendation approach that takes advantage of the increasing amount of available social data and specifically the semantic relatedness of topics that interest users, and uses graph theory algorithms in order to calculate user interest similarity using the Topic Graph. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 36 REFERENCES
Fast Incremental and Personalized PageRank
TLDR
The overall result is that this algorithm is fast enough for real-time queries over a dynamic social network. Expand
Supervised random walks: predicting and recommending links in social networks
TLDR
An algorithm based on Supervised Random Walks is developed that naturally combines the information from the network structure with node and edge level attributes and outperforms state-of-the-art unsupervised approaches as well as approaches that are based on feature extraction. Expand
The Unified Logging Infrastructure for Data Analytics at Twitter
TLDR
This paper presents Twitter's production logging infrastructure and its evolution from application-specific logging to a unified "client events" log format, where messages are captured in common, well-formatted, flexible Thrift messages. Expand
Large-scale machine learning at twitter
TLDR
A case study of Twitter's integration of machine learning tools into its existing Hadoop-based, Pig-centric analytics platform to provide predictive analytics capabilities that incorporate machine learning, focused specifically on supervised classification. Expand
SALSA: the stochastic approach for link-structure analysis
TLDR
It is proved that SALSA is quivalent to a weighted in degree analysis of the link-sturcutre of WWW subgraphs, making it computationally more efficient than the Mutual reinforcement approach, and comparisions reveal a topological Phenomenon called the TKC effect which prevents the Mutual Reinforcement approach from identifying meaningful authorities. Expand
On the precision of social and information networks
TLDR
This paper proves that the Kronecker-graph based generative model of Leskovec et al. satisfies an appropriate and natural definition of user interests, and shows that this model also has high precision, high recall, and low diameter. Expand
Design patterns for efficient graph algorithms in MapReduce
TLDR
Three design patterns are presented that address issues and can be used to accelerate a large class of graph algorithms based on message passing, exemplified by PageRank, and are shown to reduce the running time of PageRank on a web graph with 1.4 billion edges by 69%. Expand
A Survey of Link Prediction in Social Networks
TLDR
This article surveys some representative link prediction methods by categorizing them by the type of models, largely considering three types of models: first, the traditional (non-Bayesian) models which extract a set of features to train a binary classification model, and second, the probabilistic approaches which model the joint-probability among the entities in a network by Bayesian graphical models. Expand
Community Structure in Large Networks: Natural Cluster Sizes and the Absence of Large Well-Defined Clusters
TLDR
This paper employs approximation algorithms for the graph-partitioning problem to characterize as a function of size the statistical and structural properties of partitions of graphs that could plausibly be interpreted as communities, and defines the network community profile plot, which characterizes the "best" possible community—according to the conductance measure—over a wide range of size scales. Expand
Automatic management of partitioned, replicated search services
TLDR
The distributed search architecture that underlies Twitter user search, a service for discovering relevant accounts on the popular microblogging service, makes use of the principle that eliminates the distinction between failure and other anticipated service disruptions, which leads to greater robustness and fault-tolerance. Expand
...
1
2
3
4
...