Less is More: Semi-Supervised Causal Inference for Detecting Pathogenic Users in Social Media

Alvari, Hamidreza; Shaabani, Elham; Sarkar, Soumajyoti; Beigi, Ghazaleh; Shakarian, Paulo

doi:10.1145/3308560.3316500

Cited by 31 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ease of using the Internet has raised numerous security and privacy issues. Mitigating these concerns has been studied from different aspects such as identifying malicious activities [2][3][4][5], addressing users' privacy issues [7,9,11,13], and studying signed links [8,12,14,15,88,90]. Link analysis [58,89] is amongst the most popular research directions (e.g., information spread [52] and opinion formation [51]) to understand users' behavior in social networks.…”

Section: Related Workmentioning

confidence: 99%

“…Positive or negative attitudes between users assign positive or negative signs to links. Examples include trust/distrust on Epinions, 1 friend/foe on Slashdot, 2 and vote/dispute on Wikipedia. 3 Positive links are important in helping users find relevant and credible information online [90] and benefit many applications such as recommendation and information filtering [89].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Social Science–guided Feature Engineering

Beigi

Tang

Liu

2020

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

Many real-world relations can be represented by signed networks with positive links (e.g., friendships and trust) and negative links (e.g., foes and distrust). Link prediction helps advance tasks in social network analysis such as recommendation systems. Most existing work on link analysis focuses on unsigned social networks. The existence of negative links piques research interests in investigating whether properties and principles of signed networks differ from those of unsigned networks and mandates dedicated efforts on link analysis for signed social networks. Recent findings suggest that properties of signed networks substantially differ from those of unsigned networks and negative links can be of significant help in signed link analysis in complementary ways. In this article, we center our discussion on a challenging problem of signed link analysis . Signed link analysis faces the problem of data sparsity, i.e., only a small percentage of signed links are given. This problem can even get worse when negative links are much sparser than positive ones as users are inclined more toward positive disposition rather than negative. We investigate how we can take advantage of other sources of information for signed link analysis. This research is mainly guided by three social science theories, Emotional Information , Diffusion of Innovations , and Individual Personality . Guided by these, we extract three categories of related features and leverage them for signed link analysis. Experiments show the significance of the features gleaned from social theories for signed link prediction and addressing the data sparsity challenge.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Social Science–guided Feature Engineering

Beigi

Tang

Liu

2020

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The ease of using the Internet has raised numerous security and privacy issues. Mitigating these concerns has been studied from different aspects such as identifying malicious activities [2][3][4][5], addressing users' privacy issues [7,9,11,13] and studying signed links [8,12,14,15,88,90]. Link analysis [58,89] is amongst the most popular research directions (e.g., information spread [52], opinion formation [51]) to understand users' behavior in social networks.…”

Section: Related Workmentioning

confidence: 99%

Social Science Guided Feature Engineering: A Novel Approach to Signed Link Analysis

Beigi,

Tang,

Liu

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Many real-world relations can be represented by signed networks with positive links (e.g., friendships and trust) and negative links (e.g., foes and distrust). Link prediction helps advance tasks in social network analysis such as recommendation systems. Most existing work on link analysis focuses on unsigned social networks. The existence of negative links piques research interests in investigating whether properties and principles of signed networks differ from those of unsigned networks, and mandates dedicated efforts on link analysis for signed social networks. Recent findings suggest that properties of signed networks substantially differ from those of unsigned networks and negative links can be of significant help in signed link analysis in complementary ways. In this article, we center our discussion on a challenging problem of signed link analysis. Signed link analysis faces the problem of data sparsity, i.e. only a small percentage of signed links are given. This problem can even get worse when negative links are much sparser than positive ones as users are inclined more towards positive disposition rather than negative. We investigate how we can take advantage of other sources of information for signed link analysis. This research is mainly guided by three social science theories, Emotional Information, Diffusion of Innovations, and Individual Personality. Guided by these, we extract three categories of related features and leverage them for signed link analysis. Experiments show the significance of the features gleaned from social theories for signed link prediction and addressing the data sparsity challenge.

show abstract

“…Balancing neural networks (BNNs) [17] aim to obtain balanced representations of a treatment groups and a control group by minimizing the discrepancy between them, such as the Wasserstein distance [33]. Most recently, some studies have addressed causal inference problems on network-structured data [13,2,36]. Alvari et al applied the idea of manifold regularization using users activities as causality-based features to detect harmful users in social media [2].…”

Section: Treatment Effect Estimationmentioning

confidence: 99%

Counterfactual Propagation for Semi-Supervised Individual Treatment Effect Estimation

Harada

Kashima

2020

Preprint

View full text Add to dashboard Cite

Individual treatment effect (ITE) represents the expected improvement in the outcome of taking a particular action to a particular target, and plays important roles in decision making in various domains. However, its estimation problem is difficult because intervention studies to collect information regarding the applied treatments (i.e., actions) and their outcomes are often quite expensive in terms of time and monetary costs. In this study, we consider a semi-supervised ITE estimation problem that exploits more easily-available unlabeled instances to improve the performance of ITE estimation using small labeled data. We combine two ideas from causal inference and semi-supervised learning, namely, matching and label propagation, respectively, to propose counterfactual propagation, which is the first semi-supervised ITE estimation method. Experiments using semi-real datasets demonstrate that the proposed method can successfully mitigate the data scarcity problem in ITE estimation.

show abstract

Less is More: Semi-Supervised Causal Inference for Detecting Pathogenic Users in Social Media

Cited by 31 publications

References 27 publications

Social Science–guided Feature Engineering

Social Science–guided Feature Engineering

Social Science Guided Feature Engineering: A Novel Approach to Signed Link Analysis

Counterfactual Propagation for Semi-Supervised Individual Treatment Effect Estimation

Contact Info

Product

Resources

About