System and Technique for Influence Estimation on Social Media Networks Using Causal Inference

In the realm of social media, content influence and its quantification have been elusive targets. There's a true need for well-defined, systematic methods for measuring influence with higher accuracy to understand information dissemination better. Social media platforms are complex networks, with content much like a flowing river that can shift directions at any point. This dynamic nature of data flow and its influence creates an opportunity and need for more advanced detection systems. The problem with current approaches is the overemphasis on the content's immediate reach or popularity. Traditional methods fail to capture the narrative behind the data spread or understand the level of influence on the recipients. They also fall short in tracking the root of the influence, tracing its ripple effect in the network, and quantifying it accurately. Therefore, existing techniques can give partial or skewed results, contributing to misinformed strategic decisions.

Technology Description

This technology focuses on a three-pronged approach toward influence detection and quantification. It uses a network sampling processor that samples information from various social media networks. Additionally, it contains a narrative discovery processor, which takes in the sampled information and identifies a narrative connected to a subset of the sampled information. Lastly, an influence quantification processor receives information related to the identified narrative and measures the influence of the narrative on the social media networks through a network causal inference process. The distinguishing factor of this technology lies in its methodical, systematic approach toward influence detection and quantification on social media. Instead of focusing solely on the content, it leverages the flow and dissemination of information via narratives. Moreover, by tracing the narrative's influence through a network causal inference process, it provides a deeper, more comprehensive understanding of how influence spreads and manifests within a network, thereby offering a higher level of accuracy compared to traditional methods.