WTF: the who to follow service at Twitter
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
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 architectural complexity and allowed us to develop and deploy the service in only a few months. At the core of our architecture is Cassovary, an open-source in-memory graph processing engine we built from scratch for WTF. Besides powering Twitter's user recommendations, Cassovary is also used for search, discovery, promoted products, and other services as well. We describe and evaluate a few graph recommendation algorithms implemented in Cassovary, including a novel approach based on a combination of random walks and SALSA. Looking into the future, we revisit the design of our architecture and comment on its limitations, which are presently being addressed in a second-generation system under development.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
MapReduce: simplified data processing on large clusters
Dean, J., & Ghemawat, S. (2008) · Communications of the ACM · doi:10.1145/1327452.1327492 · Cited by 18,476
(1999) · Cited by 12,854
Authoritative sources in a hyperlinked environment
Kleinberg, J. M. (1999) · Journal of the ACM · doi:10.1145/324133.324140 · Cited by 8,959
A Bridging Model for Parallel Computation
Valiant, L. G. (1990) · ACM eBooks · doi:10.1145/3749740.3749753 · Cited by 3,664
Pregel: a system for large-scale graph processing
Malewicz, G., Austern, M. H., Bik, A. J. C., Dehnert, J. C., Horn, I., Leiser, N., & Czajkowski, G. (2010) · Proceedings of the 2010 ACM SIGMOD International Conference on Management of data · doi:10.1145/1807167.1807184 · Cited by 3,515
Leskovec, J., Lang, K. J., Dasgupta, A., & Mahoney, M. W. (2009) · Internet Mathematics · doi:10.1080/15427951.2009.10129177 · Cited by 1,872
Pig latin: a not-so-foreign language for data processing
Olston, C., Reed, B., Srivastava, U., Kumar, R., & Tomkins, A. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376726 · Cited by 1,730
Multilevelk-way Partitioning Scheme for Irregular Graphs
Karypis, G., & Kumar, V. (1998) · Journal of Parallel and Distributed Computing · doi:10.1006/jpdc.1997.1404 · Cited by 1,675
Distributed GraphLab: a framework for machine learning and data mining in the cloud
Low, Y., Bickson, D., Gonzalez, J., Guestrin, C., Kyrola, A., & Hellerstein, J. M. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2212351.2212354 · Cited by 1,653
Supervised random walks: predicting and recommending links in social networks
Backstrom, L., & Leskovec, J. (2011) · Proceedings of the fourth ACM international conference on Web search and data mining · doi:10.1145/1935826.1935914 · Cited by 982
Twister: a runtime for iterative MapReduce
Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S.-H., Qiu, J., & Fox, G. (2010) · Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing · doi:10.1145/1851476.1851593 · Cited by 777
HaLoop: efficient iterative data processing on large clusters
Bu, Y., Howe, B., Balazinska, M., & Ernst, M. D. (2010) · Proceedings of the VLDB Endowment · doi:10.14778/1920841.1920881 · Cited by 693
A Survey of Link Prediction in Social Networks
Hasan, M. A., & Zaki, M. J. (2011) · Social Network Data Analytics · doi:10.1007/978-1-4419-8462-3_9 · Cited by 566
Scalable SPARQL querying of large RDF graphs
Huang, J., Abadi, D. J., & Ren, K. (2011) · Proceedings of the VLDB Endowment · doi:10.14778/3402707.3402747 · Cited by 461
Data-intensive text processing with MapReduce
Lin, J., & Dyer, C. (2009) · Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Tutorial Abstracts on - NAACL '09 · doi:10.3115/1620950.1620951 · Cited by 445
Self-citationBuilding a high-level dataflow system on top of Map-Reduce: the Pig experience
Gates, A. F., Natkovich, O., Chopra, S., Kamath, P., Narayanamurthy, S. M., Olston, C., Reed, B., Srinivasan, S., & Srivastava, U. (2009) · Proceedings of the VLDB Endowment · doi:10.14778/1687553.1687568 · Cited by 405
Practical guide to controlled experiments on the web: listen to your customers not to the hippo
Kohavi, R., Henne, R. M., & Sommerfield, D. (2007) · Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1281192.1281295 · Cited by 377
SALSA: the stochastic approach for link-structure analysis
Lempel, R., & Moran, S. (2001) · ACM Transactions on Information Systems · doi:10.1145/382979.383041 · Cited by 362
On compressing social networks
Chierichetti, F., Kumar, R., Lattanzi, S., Mitzenmacher, M., Panconesi, A., & Raghavan, P. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557049 · Cited by 349
Fast incremental and personalized PageRank
Bahmani, B., Chowdhury, A., & Goel, A. (2010) · Proceedings of the VLDB Endowment · doi:10.14778/1929861.1929864 · Cited by 327
Self-citationTowards Scaling Fully Personalized PageRank: Algorithms, Lower Bounds, and Experiments
Fogaras, D., Rácz, B., Csalogány, K., & Sarlós, T. (2005) · Internet Mathematics · doi:10.1080/15427951.2005.10129104 · Cited by 282
Large-scale machine learning at twitter
Lin, J., & Kolcz, A. (2012) · Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data · doi:10.1145/2213836.2213958 · Cited by 219
Self-citationDesign patterns for efficient graph algorithms in MapReduce
Lin, J., & Schatz, M. (2010) · Proceedings of the Eighth Workshop on Mining and Learning with Graphs · doi:10.1145/1830252.1830263 · Cited by 167
Self-citationPrIter: a distributed framework for prioritized iterative computations
Zhang, Y., Gao, Q., Gao, L., & Wang, C. (2011) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/2038916.2038929 · Cited by 144
Managing large dynamic graphs efficiently
Mondal, J., & Deshpande, A. (2012) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/2213836.2213854 · Cited by 109
The unified logging infrastructure for data analytics at Twitter
Lee, G., Lin, J., Liu, C., Lorek, A., & Ryaboy, D. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2367502.2367516 · Cited by 90
Self-citationMapreduce is Good Enough?If All You Have is a Hammer, Throw Away Everything That's Not a Nail!
Lin, J. (2012) · Big Data · doi:10.1089/big.2012.1501 · Cited by 90
Self-citationOn the precision of social and information networks
Zadeh, R. B., Goel, A., Munagala, K., & Sharma, A. (2013) · Conference on Online Social Networks · doi:10.1145/2512938.2512955 · Cited by 34
Self-citation
Cited by
Exposure to opposing views on social media can increase political polarization
Bail, C. A., Argyle, L. P., Brown, T. W., Bumpus, J. P., Chen, H., Hunzaker, M. B. F., Lee, J., Mann, M., Merhout, F., & Volfovsky, A. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1804840115 · Cited by 1,863
Boutyline, A., & Willer, R. (2017) · Political Psychology · doi:10.1111/pops.12337 · Cited by 491
TriRank: Review-aware Explainable Recommendation by Modeling Aspects
He, X., Chen, T., Kan, M.-Y., & Chen, X. (2015) · Proceedings of the 24th ACM International on Conference on Information and Knowledge Management · doi:10.1145/2806416.2806504 · Cited by 456
One trillion edges: graph processing at Facebook-scale
Ching, A., Edunov, S., Kabiljo, M., Logothetis, D., & Muthukrishnan, S. (2015) · Proceedings of the VLDB Endowment · doi:10.14778/2824032.2824077 · Cited by 404
Information network or social network?: the structure of the twitter follow graph
Myers, S. A., Sharma, A., Gupta, P., & Lin, J. (2014) · Proceedings of the 23rd International Conference on World Wide Web · doi:10.1145/2567948.2576939 · Cited by 313
Self-citation
Metadata
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.