Signed Network Embedding in Social Media

Wang, Suhang; Tang, Jiliang; Aggarwal, Charų C.; Chang, Yi; Liu, Huan

doi:10.1137/1.9781611974973.37

Cited by 209 publications

(169 citation statements)

References 29 publications

Supporting

Mentioning

162

Contrasting

Order By: Relevance

“…Our future work will first consist of gaining an even better understanding of the dynamics of signed bipartite networks and how social theories such as balance theory affect their construction/evolution. Thereafter, we plan to utilize signed butterflies for other network analysis tasks in the signed bipartite setting such as network embedding [10,44] and tie strength prediction [46]. We also plan to further pursue the usefulness of the signed bipartite network formulation of the US Congress for in-depth analysis and prediction tasks such as "swing votes", which are votes coming from a representatives that is voting against what their party suggests.…”

Section: Resultsmentioning

confidence: 99%

“…In signed networks one of the most fundamentally studied social theories is balance theory [6,17], which discusses the settings in signed networks that are socially "balanced" (i.e., stable), and those that are more likely to change (to be balanced) due to the social tensions involved in maintaining "unbalanced" and seemingly unnatural connections. In recent signed network analysis works balance theory is usually investigated and then applied towards many tasks [28,39,44], but almost always in the form of triangles (or cycles of length 3) in a unipartite signed network. As seen in Figure 1, there are four possible configurations between the three nodes.…”

Section: Signed Butterflies In Bipartite Networkmentioning

confidence: 99%

See 1 more Smart Citation

Balance in Signed Bipartite Networks

Derr

Johnson

Chang

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

A large portion of today's big data can be represented as networks. However, not all networks are the same, and in fact, for many that have additional complexities to their structure, traditional general network analysis methods are no longer applicable. For example, signed networks contain both positive and negative links, and thus dedicated theories and algorithms have been developed. However, previous work mainly focuses on the unipartite setting where signed links connect any pair of nodes. Signed bipartite networks on the one hand, are commonly found, but have primarily been overlooked. Their complexities of having two node types where signed links can only form across the two sets introduce challenges that prevent most existing literature on unipartite signed and unsigned bipartite networks from being applied. On the other hand, balance theory, a key signed social theory, has been generally defined for cycles of any length and is being used in the form of triangles for numerous unipartite signed network tasks. However, in bipartite networks there are no triangles and furthermore there exist two types of nodes. Therefore, in this work, we conduct the first comprehensive analysis and validation of balance theory using the smallest cycle in signed bipartite networks -signed butterflies (i.e., cycles of length 4 containing the two node types). Then, to investigate the applicability of balance theory aiding signed bipartite network tasks, we develop multiple sign prediction methods that utilize balance theory in the form of signed butterflies. Our sign prediction experiment on three real-world signed bipartite networks demonstrates the effectiveness of using these signed butterflies for not only sign prediction, but paves the way for improvements in other signed bipartite network analysis tasks.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Signed Butterflies In Bipartite Networkmentioning

confidence: 99%

Balance in Signed Bipartite Networks

Derr

Johnson

Chang

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Beyond first order and second order proximities, AROPE [34] is a model that supports shifts across arbitrary order proximities based on SVD framework. In addition, there are some deep neural network based methods such as SDNE [27], SDAE [6], and SiNE [30], which introduce deep models to fit network data. The methods described above are mainly designed for homogeneous networks where the types of nodes are the same.…”

Section: Related Workmentioning

confidence: 99%

Hyper-Path-Based Representation Learning for Hyper-Networks

Huang

Liu

Song

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Network representation learning has aroused widespread interests in recent years. While most of the existing methods deal with edges as pairwise relationships, only a few studies have been proposed for hyper-networks to capture more complicated tuplewise relationships among multiple nodes. A hyper-network is a network where each edge, called hyperedge, connects an arbitrary number of nodes. Different from conventional networks, hyper-networks have certain degrees of indecomposability such that the nodes in a subset of a hyperedge may not possess a strong relationship. That is the main reason why traditional algorithms fail in learning representations in hyper-networks by simply decomposing hyperedges into pairwise relationships. In this paper, we firstly define a metric to depict the degrees of indecomposability for hyper-networks. Then we propose a new concept called hyper-path and design hyperpath-based random walks to preserve the structural information of hyper-networks according to the analysis of the indecomposability. Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks. Finally, we conduct extensive experiments on several real-world datasets covering the tasks of link prediction and hyper-network reconstruction, and results demonstrate the rationality, validity, and effectiveness of our methods compared with those existing state-of-the-art models designed for conventional networks or hyper-networks.

show abstract

“…However, these methods can only address unsigned and homogeneous networks. Additionally, several studies focus on representation learning in the scenario of heterogeneous network [3,32], attributed network [10], or signed network [29,33]. However, these methods are specialized in only one particular type of networks, which is not applicable to the problem of sentiment prediction in real-world signed and heterogeneous networks.…”

Section: Network Embeddingmentioning

confidence: 99%

Shine

Wang

Zhang

Hou

et al. 2018

Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining

285

View full text Add to dashboard Cite

In online social networks people often express attitudes towards others, which forms massive sentiment links among users. Predicting the sign of sentiment links is a fundamental task in many areas such as personal advertising and public opinion analysis. Previous works mainly focus on textual sentiment classification, however, text information can only disclose the "tip of the iceberg" about users' true opinions, of which the most are unobserved but implied by other sources of information such as social relation and users' profile. To address this problem, in this paper we investigate how to predict possibly existing sentiment links in the presence of heterogeneous information. First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users' sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method. Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users' latent representations from heterogeneous networks and predict the sign of unobserved sentiment links. SHINE utilizes multiple deep autoencoders to map each user into a low-dimension feature space while preserving the network structure. We demonstrate the superiority of SHINE over state-of-the-art baselines on link prediction and node recommendation in two real-world datasets. The experimental results also prove the efficacy of SHINE in cold start scenario.

show abstract

Signed Network Embedding in Social Media

Cited by 209 publications

References 29 publications

Balance in Signed Bipartite Networks

Balance in Signed Bipartite Networks

Hyper-Path-Based Representation Learning for Hyper-Networks

Shine

Contact Info

Product

Resources

About