The slashdot zoo: mining a social network with negative edges

By J´erˆome Kunegis, Andreas Lommatzsch, Christian Bauckhage. The Web Conference, 2009

501 citations recorded by the source corpus.

We analyse the corpus of user relationships of the Slashdot technology news site. The data was collected from the Slashdot Zoo feature where users of the website can tag other users as friends and foes, providing positive and negative endorsements. We adapt social network analysis techniques to the problem of negative edge weights. In particular, we consider signed variants of global network characteristics such as the clustering coefficient, node-level characteristics such as centrality and popularity measures, and link-level characteristics such as distances and similarity measures. We evaluate these measures on the task of identifying unpopular users, as well as on the task of predicting the sign of links and show that the network exhibits multiplicative transitivity which allows algebraic methods based on matrix multiplication to be used. We compare our methods to traditional methods which are only suitable for positively weighted edges.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/ea1b04b65e62d4debb2d4c2d7a92d95408be15f0

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 Statistical and Nonlinear Physics

Citations in the corpus

Deep Network Embedding for Graph Representation Learning in Signed Networks (2019, background): “The Slashdot dataset [50] is a signed social network extracted from the technology news site Slashdot, where users can form the relationships as friends (positive) or foes (negative).”
The Index-Based Subgraph Matching Algorithm with General Symmetries (ISMAGS): Exploiting Symmetry for Faster Subgraph Enumeration (2014, unknown): “The Slashdot network [24] represents ‘‘friend’’ and ‘‘foe’’ relations between users of the technology-centred Slashdot community.”
Circuit Theory and Model-Based Inference for Landscape Connectivity (2013, unknown): “…(Zhu and Klein 1996; Klein et al. 2004), collaborative recommendation (Fouss et al. 2007), communications network analysis (Tizghadam and Leon-Garcia 2010, 2011), social network analysis (Kunegis, Lommatzsch, and Bauckhage 2009), and random walks on a graph (Chandra et al. 1996; Volchenkov 2011).”
Spectral Analysis of Signed Graphs for Clustering, Prediction and Visualization (2010, background): “Zoo is a social network with " friend " and " foe " links extracted from technology news website Slashdot [17].”
Link Prediction in Complex Networks: A Survey (2010, background): “For example, a social network may consist of positive and negative links, respectively pointing to friends and foes [161], or trusted and distrusted peers [162].”
Negative Link Prediction in Social Media (2014, background): “The recent availability of signed social networks in social media sites such as Epinions and Slashdot has motivated increasing research on signed network analysis [11, 13, 3].”
State of the aRt personality research: A tutorial on network analysis of personality data in R (2015, unknown): “Transitivity has been extended Running Head: STATE OF THE ART PERSONALITY REASERCH by Opsahl and Panzarasa (2009) to take into account edge weights and directions, and by Kunegis and collaborators to signed networks (Kunegis et al., 2009).”
A Comprehensive Survey on Community Detection With Deep Learning (2021, unknown): “Signed Networks Epinions [138] 7,000 404,006 (positive) + 47,143 (negative) Slashdot [139] 7,000 181,354 (positive) + 56,675 (negative) Wiki [140] 7,118 81,318 (positive) + 22,357 (negative) -”
A Survey on Troll Detection (2020, methodology): “For example, in [35] researchers try to improve this method by implementing an algorithm that, at each iteration, reduces the size of the social network.”
A Survey of Signed Network Mining in Social Media (2015, methodology): “Examples of signed networks in social media include trust/distrust in Epinions1 [Massa and Avesani 2005; Leskovec et al. 2010a] and friends/foes in Slashdot2 [Kunegis et al. 2009].”
Predicting positive and negative links in online social networks (2010, background): “For example, users on Wikipedia can vote for or against the nomination of others to adminship [3]; users on Epinions can express trust or distrust of others [8, 18]; and participants on Slashdot can declare others to be either “friends” or “foes” [2, 13, 14].”
Signed Graph Convolutional Networks (2018, background): “While some problems such as link sign prediction [18], [21] and centrality [22] have been heavily explored, other directions such as network modeling [23], node relevance [24], and network embedding [19] are still in early development [25].”
Predicting positive and negative links in signed social networks by transfer learning (2013, methodology): “did spectral analysis on signed networks [11, 12].”
Signed networks in social media (2010, background): “, [1, 15, 16]), research in on-line social networks has focused on contexts in which the interactions have largely only positi ve interpretations — that is, connecting people to their frien ds, fans, followers, and collaborators.”