Skip to main content

Reason Based Text Alignment Discovery Model

The hottest topic currently is fake news and the proliferation of disinformation. Though it would be counter to the wishes of corporations more interested in profits than human collective good, a system is sorely required to analyse text content that is shared as & undistinguishable from facts. Small statements with no backing and linking to articles written based on pure emotion rather than concrete evidence, backed by nothing aside from straw man arguments or espousing opiníon and rhetoric as law or common decree.

An outline for a model that would generate a small visual graph which would allow for a glance into the substance of the content before consumption:
  • Emotive language ratio to detailing of findings and reason based "disprove first" approach
  • Inference of subtext and agenda of the content
  • Links + source references count & meta score of their own merit
  • Ratio of steel man or straw man arguments
  • Count of balacing statements and justification/testing of hypothesis
  • Count for reference to opposing views with contextual ratio of emotional tone vs analytical debate
Such a model would need a vast knowledge of textual reference and some careful tuning + coaching to avoid biases and proliferation of skewed views. True balancing and reason based "disprove first" approach would need to be cornerstone of the algorithm.

Comments

Popular posts from this blog

Galliventurer - Dreaming of a Universe

n. Galliventurer - one who adventures whilst gallivanting. We have a name. A compound of the words gallivanter & adventurer it fits the game quite nicely. It will also be the name of the player's ship (though, you may be able to have many ships throughout the game). Also trying something a little different for this project, practicing what I preach as it were. I'm actually going to plan this out a little bit before I ever actually write any code. Oddly I feel that most of my hair brain schemes of previous years have had a fast paced "rush to market before someone else thinks of this" attitude. So obviously there was no time to stop and take a moment to put any thought in before code went into editor. None of those projects ever made it out of the proof of concept phase oddly enough, no prizes for working out why. In the spirit of all this, things are different this time around. Having given it even two minutes of thought there are several issues....

How to Think

Moving an arm and thinking about moving an arm are two vastly different things. Even thinking about thinking about moving an arm is a natural thing to do even if reading it is very odd. Now the hard part, how to you design thinking ? The deliberate process of simulating scenarios to either logical or illogical ends would seem like a great fit for computers that can do millions of calculations a second. The slow an deliberate winding down a thought path seems to be the missing link to truely intelligent machines. We are very good at making machines. Even more so machines that actually produce things and have purpose. Since the earliest primitive forms of man, our tools are defined by their use. Or more aptly by the end result they achieve. So what is the end result of smart machines? To drive our cars, build our structures, do the heavy lifting and manage our lives? To do all that the ability to compute and apply action is needed but not actual thought. Most business tools and modern ap...