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。

Some BBC election result stories were computer-generated

58 点作者 rajeshrajappan超过 5 年前

12 条评论

hanoz超过 5 年前
<i>&gt; How computers wrote</i><p>Hmmm... Googling: &quot;elected as the MP for&quot; &quot;was created using some automation&quot;, reveals very little variation. We&#x27;re not exactly talking AI powered journalism here. More mail merge than ML.<p>Next week: How computers wrote your last electricity bill.
评论 #21783004 未加载
评论 #21784421 未加载
grammarxcore超过 5 年前
I worked at a startup in 2015 that did something similar. Using an NLP called Yseop, we wrote sports articles. The team consisted of me on backend, a journalist writing the Yseop code, a technical writer building the story trees, and a data scientist building the DBs from a plethora of sports sources. It&#x27;s fairly straightforward. Provide enough variation and you don&#x27;t lose readers.<p>Yseop is not cheap, though, and the company went under after massive financial fraud. The Tribune Network used a fair chunk of our content at the time. I&#x27;ve been waiting for this to be more common-place.
评论 #21784123 未加载
PeterStuer超过 5 年前
&quot;That would never have been possible using humans&quot;<p>That would have been <i>more</i> <i>expensive</i> using humans.<p>Factual reporting is fairly trivial to automate. Add some language generation and you can even make it sound less dry.<p>More difficult is adding local contextualization and the impact of e.g. specific local factors that might have had an influence on the vote outcome.<p>Implying &#x27;the computer&#x27; is doing anything here that a dedicated human could not is just bad communication at best and utter lies at worst.
评论 #21783815 未加载
pytester超过 5 年前
&gt;Voter turnout was down by 3.5 percentage points since the last general election.<p>hm, this example they used was my constituency. I walked around for about 15 minutes until I found the entrance because somebody moved the &quot;POLLING STATION&quot; sign against a wall where it was less clearly visible. I wonder if that&#x27;s related :&#x2F;
monkeydust超过 5 年前
Bloomberg has been running automated stories for a while - all flagged as automated so you know. Makes sense for company &#x2F; eco releases but noticed they are getting more &#x27;editorial&#x27; as well with some of newer automated stories.<p>Good piece by NYT earlier this year diving into some of the details and tech used.<p><a href="https:&#x2F;&#x2F;www.nytimes.com&#x2F;2019&#x2F;02&#x2F;05&#x2F;business&#x2F;media&#x2F;artificial-intelligence-journalism-robots.html" rel="nofollow">https:&#x2F;&#x2F;www.nytimes.com&#x2F;2019&#x2F;02&#x2F;05&#x2F;business&#x2F;media&#x2F;artificial...</a>
Rebelgecko超过 5 年前
For stories that are basically just regurgitating easily parsable statistics, this is going to become more and more common. The LA Times also has an algorithm that produces a story every time there&#x27;s a large enough earthquake reported by the USGS. The byline gives the credit to &quot;Quakebot&quot;, although the disclaimer that the article was auto-generated also credits the person who wrote the bot&#x27;s code
Wowfunhappy超过 5 年前
The information in the example story could have been communicated much more succinctly via some type of (generated) infographic. Or, heck, just a table.<p>IMO, paragraphs of text are the worst way to communicate this type of data.
a_band超过 5 年前
I guarantee that a computer didn&#x27;t write this clickbait BBC headline. :-)
georgeecollins超过 5 年前
I read stories about stocks sometimes that I think are computer generated. They sound like XYZ reported profits up 10% while margins downs 2%. Typical margins in XYZ corporation&#x27;s sector are 22%, while XY maintains a margin of 24%..&quot; etc.<p>Sometimes I think, I could get this information from reading the 10q. Still I like getting the info in paragraph form. So yay computers.
jawns超过 5 年前
About 10 years ago, as an online editor, I built a similar set of scripts -- we called them one-clicks. You&#x27;d click a button, the story would be generated, and it would be populated into the CMS.<p>This works really well for mundane, data-driven stories such as lottery results or surf reports, both of which I built.<p>There are a bunch of companies, such as Narrative Science, that are doing much more sophisticated versions of this. You give them the data and they can churn out a machine-generated recap of a Little League game that reads much like an MLB story.<p>But what I think will really be a game changer is personalization for the reader.<p>Can you imagine the same story written 10 different ways for 10 reader personas? Maybe a reader with an education background might get a different lede than a reader with an interest in politics on a story about a new school district referendum. Or heck, maybe a Republican reader might get a different version of a Trump story than a Democrat. (Not that this would necessarily be a GOOD thing. But imagine the possibilities!)
ossworkerrights超过 5 年前
Content farm generators used to do something similar over 10 years ago.
pstuart超过 5 年前
Most &quot;mainstream media&quot; reports on elections solely on the basis of the horserace aspect of it. We hear very little about the actual policies proposed and the arguments for and against them.<p>I wonder why?
评论 #21783280 未加载