This blog is part of a series, AYLIEN NEWS API: A Starter Guide for Python Users. You can view the Jupyter Notebook learner document here.


So far in this series we have looked at how AYLIEN’s News API converts the news into a powerful, searchable database. First, we collate and enrich millions of documents every day. Every single news story is enriched and tagged making sure no document slips through the net. This provides structure to unstructured documents and makes them easily searchable and processable. 

But due to the incessant nature of news volume, analysing media at a granular document level is often not practical. In the previous blog, we introduced how the Timeseries endpoint can be used to analyse volumes of news over time, providing a highly effective macro level analysis of news coverage. 


The Trends Endpoint

The Trends endpoint picks up where we left off in that it is another aggregation of multiple stories, rather than simply reviewing granular stories. Similar to the Timeseries endpoint, we may be interested in seeing themes and patterns over time that aren't immediately apparent when looking at individual documents. The Trends endpoint allows us to see the most frequently recurring entities, concepts or keywords that appear in articles that meet our search criteria. This enables us to generalise the data and make high level assertions about content.

For example, in the screenshot of our News Intelligence dashboard below, we performed a vague search for news relating to Elon Musk. The widget entitled “Most Common Entities” - populated using the Trends Endpoint- has picked out Tesla, Neuralink and SpaceX from the news stories, all companies founded by Musk as well as car manufacturer competitors Volkswagen. Other personalities such as Bill Gates, Mark Zuckerburg and Kanye West have also been identified as entities that frequently appear in these stories related to Musk. 

Contact us if you would like a demo on the News Intelligence Dashboard.


Depending on a user’s familiarity with a subject, these high level news synopses may confirm their current understanding of the topic or else act as a springboard for further investigation, prompting curiosity to refine one’s query or using another endpoint to further understand the news. 

Have a look at how we used the Trends endpoint to analyse industry impact when COVID-19 first struck the world. 


This blog is part of a series, AYLIEN NEWS API: A Starter Guide for Python Users. You can view the Jupyter Notebook learner document here.


Other Blogs in the series:

Starter Guide 1: AYLIEN’s Story Object - a Primer on NLP Enrichment and How to Use it

Starter Guide 2: Refining Your News API Query

Starter Guide 3: How To Use The News API Timeseries Endpoint

Starter Guide 5: Starter Guide 5: How to Use the News API Clusters Endpoint

Start your Free Trial

Stay Informed

From time to time, we would like to contact you about our products and services via email.