TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Text analysis of Trump's tweets confirms he writes only the angrier Android half

5 点作者 var_explained将近 9 年前

1 comment

minimaxir将近 9 年前
&gt; A lot has been written about Trump’s mental state. But I’d really rather get inside the head of this anonymous staffer, whose job is to imitate Trump’s unique cadence (“Very sad!”), or to put a positive spin on it, to millions of followers. Is he a true believer, or just a cog in a political machine, mixing whatever mainstream appeal he can into the @realDonaldTrump concoction?<p>A large part of data analysis is avoiding bias. This article was written in an abrasive tone with the conclusion decided beforehand, and as a result, doesn&#x27;t give a neutral perspective of the data. (I&#x27;m not a Trump supporter myself, but it&#x27;s one of the reasons I am avoiding political data analysis if possible)<p>For example, as noted, there are only 3200 tweets pre-filter. Doing <i>specific</i> log-odd counts of 140 character tweets will lead to overfitting as I do not believe there is sufficient data. (Note how the most frequent words are not present in the log-odds chart)<p>The methodology is indeed clever, but it is hard for me to <i>trust</i> the results.