Modeling the debate dynamics of political communication in social media networks

In this research we propose a novel transmission model to describe the fascinating world of political marketing. To this end, we considered three characteristics: opinion-based behavior; echo chambers; and the the Opinion Inversion (O.I.) phenomenon, recently studied by Yogev Matalon, allowing users to transforms opposing content to support their side of the conflict.


We demonstrate that the optimal seed users for maximizing exposure in a with-inversion scenario drastically change from those in a setting where no inversion is possible, as even a considerably low probability of tweet inversion could result in a message being echoed, spread, and amplified by opposing users.


Paper abstract:

Social networks' ability to disseminate content to millions of users with just one click has made them a major playground for political marketing. Campaigners seek to identify a small subset of seed users in a social network to maximize the spread of influence. However, political content diffusion has a distinct nature —some users may invert a message's content before sending it onward, thereby propagating a view that contradicts the one held by the original author. Here, we developed a novel transmission model tailored to analyze the effect of debate dynamics in realistic settings of social networks. We demonstrate our model on a real-world network we developed based on a large-scale dataset of 715K tweets discussing active political content concerning the Israeli-Palestinian conflict. Our simulations reveal that even a minute probability of tweet content inversion could result in the message being echoed, spread, and amplified by opposing users. The profile of the optimal seed users who would maximize exposure, too, drastically changes, and “echo chambers” are intensified compared to a no-inversion setting. Neglecting the effect of inversion may even result in a counterproductive outcome from the perspective of the original authors. Campaigners can significantly benefit from explicitly accounting for the impact of content inversion in social networks.




#MachineLearning #NLP #Twitter

2 views0 comments