Seeking provenance of information using social media

Abstract

Social media propagates breaking news and disinformation alike fast and on an unsurpassed scale. Because of its democratizing nature, social media users can easily produce, receive, and propagate a piece of information without necessarily providing traceable information. Thus, there is no means for a user to verify the provenance (aka sources or originators) of information. The disinformation can cause tragic consequences to society and individuals. This work aims to take advantage of characteristics of social media to provide a solution to the problem of lacking traceable information. Such knowledge can provide additional context to the received information so that a user can assess how much value, trust, and validity should be placed on it. In this paper, we are studying a novel research problem that facilitates the seeking of the provenance of information for a few known recipients (less than 1% of the total recipients) by recovering the paths it has taken from its originators. The proposed methodology exploits easily computable node centralities of a large social media network. The experimental results with Facebook and Twitter datasets show that the proposed mechanism is effective in correctly identifying the additional recipients and seeking the provenance of information.

Information Acquisition and Social Media: An Analysis of Pakistani University Students

“…The findings describe that news values are also predominant on social media as well. The results have a wide gap between use of social media for local, national and international news [13]. Only 15.9% are using social media for national news and 2.1% were consuming international news.…”

Locating the contagion source in networks with partial timestamps

“…The samplepath-based approach has been applied to the SI model with partial observations [9], SIR model with partial observations [10], SIS model [11], and SIR model with multiple sources [12]. Other solutions in the literature include NETSLEUTH, an 1 http://www.weibo.com/ eigenvalue-based estimator [13], a dynamic message-passing algorithm [14] and a minimum-cost-based solution for the SI model with sparse observations [15]. None of these algorithms utilize the timestamp information, which is the focus of this paper.…”

Explaining Snapshots of Network Diffusions: Structural and Hardness Results

“…For each set of nodes, they define a cost function that represents the difference of the expected final set of activated nodes and the actual observed snapshot, and try to minimize that function. Finally, assuming that information propagates in a social network following the IC model, Gundecha et al in [8] study the problem of finding initial sources as well as other recipients of some information given only a small fraction of the recipients of the information. Even though the problem is NP-hard, they provide an efficient heuristic algorithm that they test with real social media datasets.…”