Scrape two news articles on the same topic and let AI compare their tone and sentiment side by side.
Marcus Johansson
October 13, 2023 · 2 min read
About this video
In this workflow, we begin by utilizing the AI Interpolator ScrapingBot module to extract content from CNN and FOX News. I'm looking to obtain articles related to Generative AI from both sources. The ScrapingBot module is straightforward in its application; it's tasked with retrieving the full articles, ensuring all relevant content is captured for analysis.
Once the articles are scraped, they’re fed into the AI Interpolator OpenAI module. The OpenAI algorithms, renowned for their accuracy, evaluate the content to determine the sentiment and tone. Each article is assessed independently, focusing on the inherent nuances and linguistic elements that reveal the underlying sentiments and perspectives presented in the articles.
The outcome is a clear analysis that delineates the differences in sentiment and tone between the two articles. It offers a glimpse into how each media outlet approaches the topic of Generative AI, without added complexity. This isn’t about flashy presentations or intricate displays, but a clear, concise and factual representation of the sentiments and tones embodied in the respective articles. This workflow simplifies the process of comparing content from different sources, making the task manageable and efficient.
This video is from before the AI Interpolator module became AI Automators, part of the AI module. Module and menu names have changed since, and some steps look different today.
Watch the video
This video is hosted on YouTube, which sets cookies once it loads.
0:00
Transcript
YouTube's automatic captions, lightly corrected. Click a line to jump to that moment in the video.
Chapters
·Updated ·2 min read
Other ways to consume this
The post in three sentences
A content type takes two links, one to CNN and one to Fox News, both about AI and the labor market. ScrapingBot fields scrape each article's main content, and an OpenAI rule in advanced mode uses tokens to compare both texts in eight sentences on tone and sentiment. The workflow is already set up, so the video walks through the fields and runs it once.