JUDO: Just-in-time rumour detection in streaming social platforms

Nguyen, Thanh; Nguyên, Thành Tâm; Nguyen, Thanh Thi; Vo, Bay; Jo, Jun; Nguyen, Quoc Viet Hung

doi:10.1016/j.ins.2021.04.018

Cited by 22 publications

(7 citation statements)

References 37 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also want to incorporate user feedback mechanisms to improve the system performance [64]- [67]. Tailor the approach to streaming data is also an interesting extension [68], [69].…”

Section: Discussionmentioning

confidence: 99%

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

Huynh

Tong

Nguyên

et al. 2022

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

Location-based social networks (LBSNs) have emerged over the past few years. Their exponential network effects depend on the fact that each user can share her daily digital footprints with different communities, in different places, and at different times (for example in the form of check-in activities). Unlike other types of social networks, activities in an LBSN can potentially be performed by several users in a collaborative way. Existing studies of representation learning for LBSNs often consider them as regular graphs and ignore these high-order, dynamic, and multi-role contexts, since their holistic interactions are quite difficult to capture. In this paper, we propose a model in which these holistic interactions can be learned and transferred into node embeddings derived from a hypergraph representation and a persona decomposition process. More specifically, the model learns from friendship edges, check-in hyperedges, and node personas at the same time, and devises multiple presentations for each user that reflects their multiple roles in a social context. The embedding learning process also exploits useful patterns such as user colocation and sequential effects through a carefully designed point-of-interest splitting step. Extensive experiments on real and synthetic datasets show that our model outperforms alternative state-of-the-art embedding methods on friendship and location prediction tasks by an average margin of 45.7% and 29.46%, respectively. We also demonstrate the robustness of our model against adversarial conditions such as structural noise, attribute noise, and hyperparameter sensitivity.

show abstract

“…We also want to incorporate user feedback mechanisms to improve the system performance [64]- [67]. Tailor the approach to streaming data is also an interesting extension [68], [69].…”

Section: Discussionmentioning

confidence: 99%

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

Huynh

Tong

Nguyên

et al. 2022

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, information on the internet is often challenging to distinguish between true and false. Compared with traditional media, the internet is more likely to allow rumors to emerge unexpectedly and spread quickly [57]. Traditional media, e.g., newspapers, radio, television stations, etc., are sponsored mainly by authoritative organizations, and the content is often released in a one-to-many instance, so the information disclosed is highly reliable.…”

Section: Adverse Rumors From the Internet On Grain Production Need To...mentioning

confidence: 99%

The Role of Internet Development in China’s Grain Production: Specific Path and Dialectical Perspective

2022

View full text Add to dashboard Cite

With the development of the internet in China, information asymmetry in traditional agriculture production has been alleviated, and the information on modern agricultural technologies and production factor mobility has been widely disseminated, significantly impacting the country’s grain productivity and output. The pertinence and effectiveness of food security system arrangement can be ensured by revealing the influence of the internet on grain production. Based on the panel data of 30 provincial administrative regions in China from 1997 to 2018, a mediation model and a moderation model were used to evaluate the effect of internet development on grain output and constraints. The results showed that grain output could be promoted as internet penetration directly increases, and can also be boosted by enhancing technology usage and promoting operation scale expansion through the internet. However, the positive effect of this cycle could be inhibited by rural population aging, as there are many barriers faced by the elderly using information and communication technology (ICT). Strengthening agricultural technology utilization and promoting large-scale operation can encourage the development of rural internet, consequently improving the national food security guarantee capacity. It is equally important to simplify internet usage to alleviate the adverse impact of population aging on grain output. This study contributes to three sections of literature on (i) the factors influencing grain output, (ii) the mediating effects of the information transmission function of the internet, (iii) and the potential impact of aging in the information era. Exploring agricultural growth from an innovative perspective of the internet can provide a reference for ensuring food security and agricultural informatization.

show abstract

“…Even worse, some people with ulterior motives try to produce a public opinion that has a special effect on social interaction and economic benefits by catering to popular taste [7][8][9]. As a consequence, rumor spreading may result in public panic and huge financial losses without the proper management and intervention [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

How individuals’ relations and propagation ability affect rumor spreading in themultilayer-like networks

Sun

Han

2023

Preprint

View full text Add to dashboard Cite

An unprecedented increasing in online ties that are created on social platform makes our social relations andinfluences more complex and diverse. We hereby propose a rumor spreading model in the multilayer-like networks byincorporating strong relations and weak relations in this paper. In particular, two type of fixed topologies are servedto describe the strong relations, and the activity-driven model is used to construct the weak relations. Moreover,the differential individuals’ propagation ability is taken into consider when we present the rumor spreading model.The mean-field theory and an approximation method are employed to theoretically derive the rumor propagationthresholds, which are consistent with the simulation results. Further research results show that the difference ofones’ strong relations can significantly influence rumor propagation. More specifically, we find (i) the density ofrumor spreader reaches the equilibrium in a shorter time, (ii) the final density of rumor spreader is higher, while thestrong relation structure is a heterogeneous network. However, while the strong relation structure is a homogeneousnetwork and the individuals’ activity rate is negatively correlated with their propagation ability, resulting in a easierspreading of rumor. Interestingly, we get the opposite result while the strong relation structure is a heterogeneousnetwork. In addition, individuals’ propagation ability and their weak relations can affect the final density of therumor spreaders, but the effects are not identical.

show abstract

JUDO: Just-in-time rumour detection in streaming social platforms

Cited by 22 publications

References 37 publications

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

Learning Holistic Interactions in LBSNs with High-order, Dynamic, and Multi-role Contexts

The Role of Internet Development in China’s Grain Production: Specific Path and Dialectical Perspective

How individuals’ relations and propagation ability affect rumor spreading in themultilayer-like networks

Contact Info

Product

Resources

About