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

Random Generation That's Not So Random

While I do want the Galliventurer universe to be procedurally & randomly generated, I don't want it to be truly random. There needs to be a modicum of probability involved. Some weighting so that some things are rarer than others. After all we can have too many diamond covered planets or uranium based suns - as you can see I haven't actually started thinking too much about the composition of the planets, stars, etc. Keeping this probability based random selection in mind, I'm going to be using a dynamically weighted series of arrays to randomly select properties for entities in the Galliventurer universe. Using something very similar to (or based on) this article by Michael Czechowski https://observablehq.com/@nextlevelshit/rejection-sampling-in-javascript . The main bit of complexity here will be the values of a randomly selected property will affect the weights of the next selection. For example the size of a star will greatly change the weight of the probabi...

No Language

I worry there isn't words to describe the depth of my feelings. One four letter word isn't enough. It feels too small, too fragile, to contain such an ache. A strand that cuts through to the very core of my soul and anchors me to you. The breadth of comfort with you, the depth of my entwinement cannot be limited to such a word. Sitting at the center of my life, you ground me when the rigors of everyday life threaten to throw me asunder to the void. I am yours always, you are my forever.

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....

Inkie Beard

Search This Blog