# Aylien’s new natural-language add-on lets you analyze (and summarize) text in Google Drive

A natural language processing startup called Aylien released a Google Chrome add-on earlier this week that lets users analyze their text right from a spreadsheet in Google Drive. Aylien launched earlier this year, proudly touting its API-based approach to analyzing text and its focus on delivering usable products rather than cutting-edge NLP research.

I tested out the add-on, and it’s both easy and useful. It’s capable of standard tasks such as sentiment analysis, entity extraction, content extraction and classification (into preset categories), but also of summarizing long pieces of text and of breaking apart media URLs into separate fields for title, author, text, and images/media.

The free trial allows users to process 1,000 rows, which should be plenty to figure out whether it will work. Additional credits start at $10 for 1,000 rows and go up to$200 for 200,000 rows.

Sentiment analysis is the first thing most people think of when they hear NLP, but it’s usually spotty (Aylien is no exception there), so I think the other capabilities are actually more useful — especially for media companies. I put the Aylien add-on to work first on a 2013 feature I wrote about Hadoop, because it was long and included lots of names and topics.

Here’s a word cloud I created from the results, without filtering anything out. Not too shabby considering who I spoke with and what you might expect to find in a story about Hadoop.

Next — and this might have been unfair because that Hadoop article is roughly 4,000 words — I tested out the summarization feature. Here’s the 246-word summary it came up with, largely, apparently, by collecting some topic sentences. Not perfect, but one could argue that’s a fair version of the Hadoop journey up to a point.

Raymie Stata, founder and CEO of Hadoop startup VertiCloud (and former Yahoo CTO), calls MapReduce “a fantastic kind of abstraction” over the distributed computing methods and algorithms most search companies were already using: