Account credibility inference based on news-sharing networks

TL;DR

The paper tackles misinformation by inferring account credibility from information diffusion, focusing on two networks: a reshare network that encodes trust in accounts and a bipartite account-source network that encodes trust in sources. It develops a suite of centrality, diffusion, and graph embedding methods, including PageRank variants, LoCred, Reputation Scaling, HITS/Co-HITS, CoCred, and node2vec, and evaluates them on three large social media datasets. The key findings reveal two forms of credibility homophily: similar credibility among accounts that reshare each other's content and among accounts sharing similar sources, with node2vec on reshare networks delivering the strongest accuracy (ROC_AUC > 0.88). The work demonstrates practical potential for platform moderation and source assessment, while acknowledging limitations like reliance on NewsGuard labels and data platform constraints, suggesting avenues for integrating diffusion signals with other misinformation detection approaches.

Abstract

The spread of misinformation poses a threat to the social media ecosystem. Effective countermeasures to mitigate this threat require that social media platforms be able to accurately detect low-credibility accounts even before the content they share can be classified as misinformation. Here we present methods to infer account credibility from information diffusion patterns, in particular leveraging two networks: the reshare network, capturing an account's trust in other accounts, and the bipartite account-source network, capturing an account's trust in media sources. We extend network centrality measures and graph embedding techniques, systematically comparing these algorithms on data from diverse contexts and social media platforms. We demonstrate that both kinds of trust networks provide useful signals for estimating account credibility. Some of the proposed methods yield high accuracy, providing promising solutions to promote the dissemination of reliable information in online communities. Two kinds of homophily emerge from our results: accounts tend to have similar credibility if they reshare each other's content or share content from similar sources. Our methodology invites further investigation into the relationship between accounts and news sources to better characterize misinformation spreaders.

Figures (5)

• Figure 1: Pipeline for mining trust patterns from information-sharing data: trust in accounts is modeled by the reshare network (top); trust in sources can be modeled by the bipartite account-source network (middle), or a projection of it, the co-share networks (bottom). Colors represent credibility labels: orange and purple for high- and low-credibility, respectively.
• Figure 2: Retweet network constructed from the Twitter_Covid dataset. To visualize the network, we filter nodes and edges using k-core decomposition alvarez2006large ($k=3$). Colors represent credibility score: orange and purple for high- and low-credibility accounts, respectively, and gray for unlabeled accounts. Node size represents in-strength, i.e., the number of retweets by the account. Large purple nodes are known misinformation super-spreaders.
• Figure 3: Bipartite account-source network constructed from the Twitter_Covid. For visualization, only the $k=4$ core of the network is shown. Node colors represent account credibility scores: orange and purple for high- and low-credibility accounts, respectively, and gray for unlabeled accounts. Source nodes are in white. Node size represents the strength of an account node, i.e., the number of posts with links by that account.
• Figure 4: Co-share network constructed from the Twitter_Covid. Given the density of this network, we aggressively filter it for visualization. We first keep the 10% of edges with the highest weights and the 10% of nodes in the innermost core ($k=4$). Then we apply the multiscale backbone method serrano2009extracting (significance level 0.3) and retain the giant component of the backbone network. Colors represent credibility score: orange and purple for high- and low-credibility accounts, respectively; unlabeled accounts are in gray. Node sizes represent core numbers: smaller nodes are in the periphery of the network.
• Figure 5: Account embedding vectors for the Twitter_Covid dataset. Node2vec vectors representing accounts are projected onto a two-dimensional space using PCA for (a) reshare and (b) co-share networks. Colors represent account credibility scores: orange and purple for high- and low-credibility accounts respectively.