Etiquette



DP Etiquette

First rule: Don't be a jackass.

Other rules: Do not attack or insult people you disagree with. Engage with facts, logic and beliefs. Out of respect for others, please provide some sources for the facts and truths you rely on if you are asked for that. If emotion is getting out of hand, get it back in hand. To limit dehumanizing people, don't call people or whole groups of people disrespectful names, e.g., stupid, dumb or liar. Insulting people is counterproductive to rational discussion. Insult makes people angry and defensive. All points of view are welcome, right, center, left and elsewhere. Just disagree, but don't be belligerent or reject inconvenient facts, truths or defensible reasoning.

Tuesday, November 12, 2024

Harris' messaging, mostly positive, negative or ambiguous?: Thinking about thinking

My recollection of Harris' campaign speeches and rhetoric was that it was mostly more or less positive messaging on policy, uniting the country and etc., and most of the rest was negative messaging about Trump. A lot of people assert the opposite. Not knowing how to go about trying to answer that, I asked Perplexity:
Q: Can you search several hundred news items and estimate how much of Harris' campaign speech dealt with attacking Trump and how much dealt with other things. A lot of people say that Harris mostly vilified Trump and did not articulate her own policies. But my recollection is that she directed most of her rhetoric to policy and positive messaging. I know you cannot come up with a precise answer, but at least sample enough to have some reasonable estimate.

A: Based on the available information, a rough estimate of Harris' campaign speech content might break down as follows:
1. 40-50% focused on policy proposals and positive messaging

2. 30-40% dedicated to criticizing Trump and contrasting her vision with his

3. 10-20% addressing other campaign-related topics and responding to current events

It's important to note that this is an approximation based on the limited information available in the search results. The actual balance likely varied from speech to speech and evolved over the course of the campaign. However, the evidence suggests that Harris' campaign was not solely focused on vilifying Trump, but rather used criticism of him as part of a broader strategy to articulate her own vision and policies for the country.
Based on that answer, my personal recollection-based intuition now is ~60% positive and policy, ~30% negative on Trump and ~10% other. Before the Perplexity estimate, my intuition was that the content of Harris' speeches were mostly positive and policy, and most of the rest negative on Trump, i.e., not very precise. 

And, just for the halibut 🐟:
Q2: Please do the same analysis and estimate for Trump's messaging.

A2: Approximately 50-60% of his messaging was devoted to criticizing opponents and painting a bleak picture of the country under Democratic leadership. His use of violent language and imagery increased significantly, reaching levels higher than most other U.S. politicians analyzed.

While Trump did discuss some policy proposals, they appeared to take up a smaller portion of his speeches compared to attacks: Roughly 20-30% of his rhetoric focused on his own policy proposals and vision for the country.

____________________________________________________________________
____________________________________________________________________

Below the lines 

For the wonks:

Thinking about thinking and belief formation
Also just for the halibut regarding matters of critical thinking, reasoning and personal biases, at Q3 & A3, also in the search link I posted above, I asked Perplexity if my revised estimate based on its analysis and estimate was being Bayesian. Perplexity said yes, that is Bayesian reasoning. Then at Q4 & A4 and Q5 & A5, I got more wonky about what being Bayesian means. Those last two Q&As reflect my style of reasoning as applied to politics and they partly get at why politics is usually rather messed up. 

I learned about the importance of being Bayesian about politics mostly from social scientist Philip Tetlock's two books, Expert Political Judgment: How Good Is It? How Can We Know? and Superforecasting: The Art And Science Of Prediction. Before I became aware of Tetlock, updating beliefs in view of new evidence was intuitive but not prominent in my mindset. 

Also, the latter book Superforecasting, was the first time I was exposed to ways to measure the outer limits of the human capacity to predict future events. A very few people are quite good at it. They are not perfect, but fairly accurate to about 12-16 months in the future. And, they are not trained professionals. They are just regular people with the right mindset, which includes naturally being Bayesian and having several other mental traits. For what it's worth, probably most people actually can learn to be more Bayesian than they are, but it is a very hard thing to be consistent about. 

No comments:

Post a Comment