In my “how mass media reframes issues” post, I discussed at the end how the DOD is developing computational methods to detect individual bloggers whose ability to contribute to political persuasion rises above a predetermined threshold. These folks could then be excised from further dialogue using a variety of methods including the new extensions to the “criminal uses” of the Internet as well as old fashioned wiretaps (see my endgame post). In this post I would like to give a specific example using TopicLens, a software system development by the Army cyber warfare department. From the Army website:
Visually communicating credibility and trust information is a challenging problem. This demonstration will focus on TopicLens, an interactive system supporting analysis of probabilistic associations in topic-modeled data in conjunction with the structure in the underlying social network from which the modeled documents were sourced. The design consists of a hybrid view, containing a river-like representation to communicate credibility or trust that a user (or group of users) have with respect to a given topic. These factors can be assessed though an examination of a users probabilistic association with that topic, and also through examination of that user’s social network and their respective credibility within the selected topic. The design leverages interactive input mechanisms such as hovering, selection and rotation to generate informative and intuitive outputs, which can take the form of label and item highlighting, opacity variance, or connection lines, all contributing to a better understanding of topic-based trust and expertise across the network.
If you find this hard to understand then watch the video below which gives a fairly clear visual explanation of the software’s utility. The important thing is that this software tool gives authorities the ability to quickly identify the most influential actors (bloggers) in an internet discussion on any topic and target them for excision by a variety of methods.
TopicLens: A Novel Tool for Analyzing Credibility through Topic Modeling from John O'Donovan on Vimeo.