Friends and neighbors on the Web
By Lada A. Adamic, Eytan Adar. 2003
3,072 citations recorded by the source corpus.
Abstract The Internet has become a rich and large repository of information about us as individuals. Anything from the links and text on a user’s homepage to the mailing lists the user subscribes to are reflections of social interactions a user has in the real world. In this paper we devise techniques and tools to mine this information in order to extract social networks and the exogenous factors underlying the networks’ structure. In an analysis of two data sets, from Stanford University and the Massachusetts Institute of Technology (MIT), we show that some factors are better indicators of social connections than others, and that these indicators vary between user populations. Our techniques provide potential applications in automatically inferring real world connections and discovering, labeling, and characterizing communities.
Subfields: Statistical and Nonlinear Physics, Transportation, Social Sciences & Humanities
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Statistical and Nonlinear Physics
- Jure Leskovec
- Charu C. Aggarwal
- Mark Newman
- Santo Fortunato
- Neil Zhenqiang Gong
- Emilio Ferrara
- Jon M. Kleinberg
- Philip S. Yu
In Transportation
- Philippe Cudré-Mauroux
- Dingqi Yang
- Bingqing Qu
- Mads Haahr
- Elizabeth M. Daly
- Cecilia Mascolo
- Salvatore Scellato
- Jie Yang
In Social Sciences & Humanities
- Jure Leskovec
- Nan Du
- Emilio Ferrara
- Krishna P. Gummadi
- Palash Goyal
- Muhan Zhang
- Yixin Chen
- Jon M. Kleinberg
Citations in the corpus
- node2vec: Scalable Feature Learning for Networks (2016, neutral): “A general observation we can draw from the results is that the learned feature representations for node pairs significantly outperform the heuristic benchmark scores with node2vec achieving the best AUC improvement on 12.6% on the arXiv dataset over the best performing baseline (Adamic-Adar [1]).”
- A Review of Relational Machine Learning for Knowledge Graphs (2015, background): “Local similarity indices such as Common Neighbors, the Adamic-Adar index [98] or Preferential Attachment [99] derive the similarity of entities from their number of common neighbors or their absolute number of neighbors.”
- Supervised random walks: predicting and recommending links in social networks (2010, methodology): “The unsupervised methods for link prediction were extensively evaluated by Liben-Nowell and Kleinberg [21] who found that the Adamic-Adar measure of node similarity [1] performed best.”
- Graph Embedding Techniques, Applications, and Performance: A Survey (2017, methodology): “Approaches for link prediction include similarity based methods [13], [14], maximum likelihood models [15], [16], and probabilistic models [17],”
- NetGAN: Generating Graphs via Random Walks (2018, neutral): “We compare with DC-SBM, node2vec and VGAE, as well as Adamic/Adar(Adamic & Adar, 2003).”
- Identification of influencers - Measuring influence in customer networks (2008, methodology): “75 as in Adamic and Adar (2003). In the exponential diffusion model we used a decay constant of 1 which indicates no diffusion, a decay of 0.”
- Embedding Networks with Edge Attributes (2018, methodology): “One way to obtain such a set of vectors is to use metrics such as Katz Index [16], Adamic Adar [1] and Common Neighbors [21].”
- A Survey of Link Prediction in Social Networks (2011, background): “From the reported results of the existing works on link prediction , Adamic/Adar works better than the previous two metrics.”
- A Survey on Trust Modeling (2015, background): “Adamic and Adar [2003] measure similarity of two pages, incoming and outgoing, depending on whether or not it has frequent features.”
- Link Prediction Based on Graph Neural Networks (2018, background): “Adamic-Adar (AA) and resource allocation (RA) [8] are second-order heuristics, as they are calculated from up to two-hop neighborhood of the target nodes.”
- Self-similar community structure in a network of human interactions. (2002, background): “We surmise that the exchange of e-mails between individuals in organisations reveals how people interact [4, 5] and therefore provides a map of the real network structure behind the formal chart.”
- Co-author Relationship Prediction in Heterogeneous Bibliographic Networks (2011, background): “The earliest works mainly study unsupervised methods [1], [7], in which different similarity”
- Exploiting place features in link prediction on location-based social networks (2011, methodology): “Users do not add friendship connections at random with all other users but, instead, tend to prefer other users that are “close” to them, either in social sense or along other dimensions such as geographic proximity or topic interest [15, 1, 6, 19].”