Good Contents Are Everywhere, But Here, We Deliver The Best of The Best.Please Hold on!
Your address will show here +12 34 56 78


Social media is a gold mine of useful information and public opinion that is just waiting to be tapped. Right now, millions of people on social channels are talking about an immeasurable range of topics, people and organizations, all the while making their valuable opinions public and accessible.

From a marketing point of view as an organization or brand, you want to know what is being said about you (and your competitors) on social media, and how it is being said. This is no easy task, as the number of channels and sheer amount of data online continue to explode.

Enter Social Listening and Text Analysis.

Social listening involves monitoring the web and the social media channels to see what’s being said about your brand, your competitors, your industry and other key areas of interest to you. But simply listening isn’t always enough. We want to understand what we are hearing out there.

How can Text Analysis help?

Using Machine Learning and Natural Language Processing techniques, it’s easier than ever to understand and analyze social media content at scale.

To make things easy for you, we’ve put together a list of Text Analysis features (or endpoints as we call them) that are being widely used by our customers for social listening. So if you’re new to using our API this will help you get up to speed quickly.

  1. Entity & Concept Extraction
  2. Sentiment Analysis
  3. Aspect-Based Sentiment Analysis

Note: We have a really cool and easy-to-use Demo showcasing all of these features. You can test them out with your own text data (articles, tweets URLs etc) or try some of our sample queries.

Let’s begin by taking a look at the first feature on our list, extracting entities and concepts.

1. Entity & Concept Extraction

Social content contains a wealth of mentioned entities and values that can provide some really interesting and important information. The challenge is mining this information, particularly at scale. To best understand social content, you want to know the who, the what and the how much from each and every post or update.

Entity Extraction extracts named entities (people, organizations, products and locations) and values (URLs, emails, telephone numbers, currency amounts and percentages) mentioned in a body of text or web pages.



Concept Extraction extracts named entities mentioned in social posts and cross-links them to DBpedia and Linked Data entities, for greater understanding.

Concept extraction also disambiguates similarly named entities. Take Apple for example. If it is mentioned in an article is it a reference to the company or the fruit? Concept extraction analyzes the content around the word and through Machine Learning and Natural Language Processing (NLP) techniques, performs the disambiguation.



By extracting entities and concepts from social content and analyzing at scale you can gain some incredibly useful insights and get answers to key questions, such as;

  • What else are people talking about when they mention our brand/product/competitor?
  • What words, phrases, brands etc are mentioned most?
  • Are they mentioning or comparing us to other brands?
  • Are they mentioning specific people or places in relation to our brand/product/competitor?

Here’s a great example from our analysis of the Super Bowl ads battle, where we collected 120,000 tweets that mentioned, or were related to, the brands that advertised during Super Bowl 50. By listening for specific mentions of entities and concepts, you can see trends over time and pinpoint reasons for them. The spike in the center of the graph below is during the game itself, when Twitter chatter is naturally going to be at its peak. One interesting observation we made here was Budweiser’s (red) sudden sharp rise in mentions after an otherwise comparatively quiet event. Upon further investigation, we discovered that Peyton Manning had mentioned the brand, ad-lib, live on air. It’s amazing what a single celebrity mention can do for your brand! And from a marketing/social-listening perspective, it’s amazing to see this information as it happens.

The graph below is interactive so you can hover over it for more information.





Because we listened out for 15 of the top brands that advertised during the event, we were able to dive deeper to gather further brand-specific insights. The clusters below represent the most-used words in tweets mentioning Amazon. Think of how useful this visualization would be for your own marketing efforts.

As you can see, Entity & Concept Extraction can be an extremely powerful tools in your social-listening arsenal. Now we’ll take a look at how you can gauge the sentiment of social media posts – are they written in a positive or negative way?

2. Sentiment Analysis

Brand awareness and reputation are extremely important to any organization. It is therefore essential to listen to how people are talking about you on social media, whether it is relating directly to your brand, one of your products or services, or even your competitors. You want to know whether they are mentioning each of these in a positive or negative way. You want to hear the true voice of the customer. This is where Sentiment Analysis comes in.

Sentiment Analysis detects the sentiment of a social post in terms of polarity (positive or negative) and subjectivity (subjective or objective). When used, particularly at scale, it can show you how people feel towards the topics that are important to you.



Analyzing the sentiment towards your brand can help you decrease churn and improve customer support by uncovering and proactively working on improving negative trends. It can help show you what you are doing wrong before too much damage has been done, but also quickly show you what you are doing right and should therefore continue doing. Sentiment Analysis can also be used to analyze your competitors social media presence and performance. You can learn from both their social media triumphs and disasters and use this information to improve your own campaigns.

Wanna know how the public feels about your latest ad? Let’s go back to our Super Bowl analysis and look at two brands who at either end of the polarity scale – Amazon and PayPal.

In the graphs below, green represents positive sentiment and red represents negative. As you can see, Amazon’s ad was very well received. PayPal’s certainly wasn’t!


Sentiment Analysis is an essential part of social listening and plays an important role in understanding the voice of the customer. But what if we want to go a step further and discover what aspects the positive/negative sentiment is stemming from? What exactly do our customers like or dislike about us?

To answer these questions, we developed Aspect-Based Sentiment Analysis.

3. Aspect-Based Sentiment Analysis

While Sentiment Analysis provides fantastic insights and has a wide range of real-world applications, the overall sentiment of a social post won’t always pinpoint the root cause of the author’s opinion.

This is where Aspect-Based Sentiment Analysis (ABSA) comes in. With ABSA, you can dive deeper and analyze the sentiment of social content toward industry-specific aspects.




Social media content, such as tweets, facebook posts and reviews, may contain fine-grained sentiment about different aspects (e.g. a product or service) that are mentioned in the content. For instance, a review about a restaurant may contain opinionated sentences about its staff, location, food, drinks and value. This information can be highly valuable for understanding customers’ opinion about a particular service or product.


As a restaurant owner, let’s say I have received 700 online reviews that result in an overall review score of 8/10. I’m quite happy with this but clearly there is room for improvement. But where exactly? By running the customer reviews through our ABSA endpoint, I can immediately start to see what my customers like, and more importantly dislike. As an example, we analyzed a 5-star restaurant review and got the following results;

Restaurant Review

We visited here during our recent trip to Sydney and overall we were very impressed. We decided to make a reservation online, which was quick and easy with instant confirmation. It was nice to be able to view the table layout and select our own online. The location is spectacular with stunning views of the harbour and Opera House. It truly was amazing. Despite this, however, the restaurant was  only about 25% full and so the atmosphere was a bit flat. Perhaps this was to our benefit as we received top class service from our waiter, Brandon, who was not only friendly and funny but extremely knowledgeable when it came to food and wine pairings. Speaking of wine, the list was extensive – we loved it – and it took us what seemed like an hour to eventually decide on a local Shiraz. Now on to the most important aspect, the food. Our seafood starters were delicious, as were out fillet steak mains. The one and only real disappointment was the dessert which was served with no real imagination and looked like it had been purchased yesterday at the local grocery store. All in all, my favourite Sydney restaurant so far. So many positives and really good value too. Highly recommend!


ABSA Results;


As you can see from the results above, the ABSA endpoint automatically pulls industry-specific aspects (such as food, drinks, reservations and value), performs Sentiment Analysis on each aspect and gives sample sentences to indicate examples of where the the score was derived.

Although this review was extremely positive and received a 5-star rating, we can still uncover certain aspects that may be in need of improvement. Our customer was clearly not impressed with their dessert and also found the general atmosphere of the restaurant to be a bit flat.

ABSA is currently available for four industries – Airlines, Hotels, Cars and Restaurants – and we are already working on expanding this list. Here are the aspects covered for our initial four industries;




We hope this post gives you some inspiration and helps you to understand the various Text Analysis features available to you and how they can help you with your social listening efforts.


Text Analysis API - Sign up




We love hearing about the cool apps and projects that our users have created, particularly when they have done so without spending a single cent. Our Text Analysis API enables users to make up to 1,000 hits per day, indefinitely. That means you can analyze up to 1,000 URLs, tweets, customer reviews, documents etc, every day, for free!

Going forward we will be regularly sharing these awesome user-created apps to show you what is possible with a free Text Analysis API like ours and hopefully inspire you to create something cool and useful yourself.

To kick things off we’ll focus on two super cool tools, a Twitter Lead Generator called Tweelead and a Conversational UI for Slack called Somerset.

Tweelead – Created by Farhad at Taskulu

Using Sentiment Analysis to Generate Actionable Leads from Twitter

Twitter is a gold mine of useful information that is just waiting to be tapped. Because of the character limitation of tweets (140 characters but soon to be more), Twitter conversations are short, concise and immediate – making them small but powerful nuggets of public opinion. The idea behind this app is quite simple – to discover, understand and participate in Twitter conversations relating to particular keywords or brands, as they are happening in real-time.



AYLIEN user Farhad, who is co-founder and CEO of Taskulu, shows us how he uses our Text Analysis API to to generate actionable leads from Twitter. Farhad knows that Twitter is an extremely popular avenue for customers to express their opinion on a brand or service. Why? Because Twitter users don’t accept the standard reply ‘within 1-2 business days’. In fact, 72% of Twitter user who use the social network to make a complaint expect a response within an hour. As a marketer, you want to reach people who are unhappy with your competitors’ product or service, and this is exactly what Tweelead is designed to take advantage of.

“There are many people out there literally asking you to introduce your product to them so they can become your customers, but the problem is that it’s very difficult to find them!”

So we know that people out there are unhappy and therefore may be open to hearing about your product. Now how do we find them?

How it works

Tweelead gathers tweets by matching the keywords that are important to you from the Twitter Streaming API and analyzes them for positive or negative sentiment, using the AYLIEN Sentiment Analysis endpoint. The app then automatically populates a Google spreadsheet with relevant tweets, depending on your preferences. Here’s a simple example;

Negative tweets mentioning iPhone or Samsung Galaxy

As a phone manufacturer looking to increase my market share against these two competitors, I now have an auto-updating spreadsheet with my ideal target users.

Try it yourself in under 5 minutes

Farhad has published the code for generating Tweeleads on GitHub. You can also find the documentation and instructions for setting it up on the GitHub page.

Here’s what you need to do;

  1. Download the code from GitHub
  2. Create a Twitter application
  3. Open a free account with AYLIEN
  4. Copy this spreadsheet to your Google Drive.

You can follow Farhad on Twitter @farhad_hf and be sure to check out his flexible task management app Taskulu.


Somerset – Created by Sam Havens

Conversational UI or chatbot for popular messaging app Slack

As we’re sure you have noticed, chat bots, conversational UI’s and personal digital assistants are becoming more and more popular. It’s not only tech giants like Google and Facebook that get to have all the fun creating them however, as AYLIEN user Sam Havens shows us with his conversational UI for Slack, Somerset.


The Problem

Sam likes sharing interesting articles with his team on Slack but found that not everyone on the team shares the same interests. Sam then decided it would be great to be able to auto-generate a summary of an article so people can decide whether or not it is worth their time.

The Solution

Botkit and AYLIEN’s Summarization endpoint.

“After some research, I decided that Aylien’s Text Analysis API was the best product out there… a generous free tier and an easy signup process— what more can you ask for? Well, a nice SDK. And they have that too!”

Thanks Sam 🙂

So we have three key services involved here, and all can be accessed for free;

Botkit – a comprehensive set of tools for creating bots

Slack – a popular multi-platform messaging app for teams

AYLIEN Text Analysis API

Getting Started

We won’t go into too much technical detail here, as Sam has explained everything you need to know on his Medium post Building Somerset, but having quickly connected Botkit to Slack, it wasn’t long before Sam was interacting with Somerset;



Sam goes through the whole setup from familiarising yourself with Botkit to integrating with our API. Try it yourself here.

You’ll need your own AYLIEN app_id and app_key for our API which you can get by signing up here.

In no time at all, Somerset was producing immediate article summaries at Sam’s request.

“I need a summary of (URL)”



With Sam’s bot now calling our API, he could go further than just summarization. Somerset also called our Classification endpoint to classify the shared article. It then produced relevant Hashtags to be used in social media sharing;



Our API has a total of 13 endpoints that you can take advantage of should you choose to create your own conversational UI, or any other app. Perhaps you want to extract the named entities (people, places organizations etc) from an article or news story, or perhaps you would like to know whether the sentiment of a particular piece of text is positive or negative.

All these features are available on our easy-to-use demo.

You can follow Sam on Twitter @sam_havens


Have you created something interesting with our API? We would love to hear about it and who knows, you may be the star of our next User App Showcase!

Ready to get started? Click below to get access to our Free Text Analysis API.

Happy Hacking!

Text Analysis API - Sign up



As a publisher, you generate a huge amount of content and keeping it organized and accessible within your network can be a real challenge. You also know that the work doesn’t stop when you click Publish, but in fact what you do with the content after its creation can be just as important as the content creation itself.

We understand the challenges that you face in the ever-changing publishing industry. We hear about them quite a lot from our customers who are facing increased competition amid a constant battle to stay relevant and at the forefront of their readers’ minds (and screens!).

Content is at the heart of reader engagement, page views, visits, time on site, CTR’s, social shares, all of the things that matter to a publisher. Given the rate at which you need to curate and produce content today, it’s becoming even more difficult to stay on top of what you’re writing about, what’s popular and what’s driving revenue.

How can Text Analysis help?

Using Machine Learning and Natural Language Processing techniques, it’s easier than ever to understand content at scale.

To make things easy for you, we’ve put together a list of Text Analysis features (or endpoints as we call them) that are being widely used by our publishing industry customers. So if you’re new to using our API this will help you get up to speed quickly about what we can help you with;

  • Article Extraction
  • Classification (Categorization)
  • Entity & Concept Extraction
  • Summarization

Note: We have a really cool and easy-to-use online Demo showcasing all of these features – check it out 🙂


1. Article Extraction

Webpages can be noisy and cluttered, they’re often awash with an overwhelming amount of ads, images, videos and pop-ups that appear alongside informative textual content. As a publisher, separating the wheat from the chaff to extract what really matters – the story itself – can be quite the challenge, whether that’s on your own network of sites or external outlets.

Our Article Extraction endpoint is used to extract the main body of text from articles, web pages and RSS feeds. In doing this, it provides us with the ‘clean’ text data and ignores other media such as images, videos or ads.



Here’s a quick example. On the left we have a web page containing text, images, video ads and links to other stories. On the right we have the results of this same web page after we ran it through Article Extraction.




Using our Article Extraction feature allows you to easily break down a webpage and extract what matters. We extract the main body of text from a web page, the published date, the author and also any image or video present.

This means you can automatically extract what matters from an article while disregarding what doesn’t, meaning you now have a much cleaner, indexed datasource available for further analysis.


2. Classification / Categorization

Categorizing mass amounts of content is an arduous task. For the most part we rely on human input to categorize articles can work, upon submitting an article for publication the author selects some category tags. This approach can work but often times it results in further problems, it can take too long and the potential for human error and less-than-perfect classification is very high.

Wouldn’t it be easier to automatically add tags based on a taxonomy?

Our Classification by Taxonomy endpoint classifies, or categorizes, a piece of text according to your choice of taxonomy, either IPTC Subject Codes or IAB QAG.

  • IPTC News Codes – International standard for categorizing news content
  • IAB QAG – The Interactive Advertising Bureau’s quality guidelines for classifying ads


We took this article about the 2016 Masters golf tournament from the BBC website and received the following results;


What you can see in the image above is the IPTC ID code and label for the golf category and our confidence that it is a correct classification. A score of 1 reflects complete confidence in the results.


Automatically categorizing content based off a standard taxonomy means the content you produce can be easily segmented based on topics. It also means you can eliminate the all too prevalent problem of authors over-using tags.

User Spotlight: Scredible

Using advanced NLP powered by AYLIEN, the team at Scredible have created a fantastic tool for content curation, sharing and publishing. Scredible categorizes content to provide personalized content based on topics and categories so they can deliver focused, relevant content to their users.


3. Entity & Concept Extraction

Your content contains a wealth of mentioned entities and values that can provide some really interesting and important information on a piece of text. The challenge is mining this information, particularly at scale. To understand content, you want to know the who, the what and the how much from each and every article.

Entity Extraction extracts named entities (people, organizations, products and locations) and values (URLs, emails, telephone numbers, currency amounts and percentages) mentioned in a body of text or web pages.



Concept Extraction extracts named entities mentioned in a document, disambiguates and cross-links them to DBpedia and Linked Data entities, along with their semantic types (including DBpedia and types).

Concept extraction disambiguates similarly named entities. Take Apple for example. If it is mentioned in an article is it referring to the company or the fruit? The last thing you want is to recommend an article about fruit to your tech readers who have just read about the latest iOS release!

Concept extraction analyzes the content around the word and through Machine Learning and Natural Language Processing (NLP) techniques, performs the disambiguation.



By extracting entities and concepts you can produce a rich tagging system to assist with your own archiving needs, content recommendation and even ad targeting. You can easily understand what people, places, organizations, brand
s for example are mentioned in the articles you publish.

User Spotlight: Complex Media

Complex Media is a New York based media platform for youth culture that has a monthly audience of over 120 million people. Complex use entities and concepts to match video content to published articles to improve ad targeting and CTRs. By identifying mentions of celebrities, brands etc they can place relevant ads on the article page containing them. Then within that video they can display ads for mentioned brands. For example, an article that mentions both Drake and Adidas will include a video of a Drake song with an Adidas advertisement shown before it plays.


4. Summarization

Have you ever began to read a long article or story and wish you could just grab a quick summary that would give you a good overview of the text? Of course you have! And so have your readers. As content consumers in general, sometimes we want it all and sometimes we just want it fast. Either way, we have you covered.

The Summarization endpoint enables you to generate a summary of an article by automatically selecting key sentences to give a cut-down but reflective overview of the main body of text. You can choose to summarize a piece of text in 1-10 sentences.

As an example, we have taken a URL from The Guardian online and produced the following summary;


Without reading the actual full article or seeing the headline you can probably establish what this article is about after reading the 5 key sentences above, which only takes around 30 seconds.

Here’s the original article from The Guardian.


The summarization end-point provides an intelligent summary of the content you’ve analyzed. This is particularly useful when for example providing snapshot teasers to your readers or for curating both internal and external content.

User Spotlight: The Magazine Channel

The Magazine Channel use our Summarization endpoint within their flagship app, Inkworthy.


We hope this post gives you some inspiration and helps you to understand the various Text Analysis features available to you and how they can help you as a publisher.


Text Analysis API - Sign up




You may or may not know it, but Text Analysis and Natural Language Processing play a huge part in a modern day digital marketing strategy.

In this blog we’re going to dive into just how important they have become in core marketing techniques and skills such as SEO, Content Marketing & Social Listening strategy.

1. SEO

Building a Keyword List

We all know how difficult it can be embarking on a keyword strategy. We’ve all been there, you start with your top target keywords and you try and brainstorm new and relevant keywords you think are worth trying to rank for. It’s a bit of a guessing game and can be quite time consuming.

There is an easier way, leveraging the concept of semantic relatedness, how close two words are to each other, you can generate a list of words and phrases that are similar and related to your target keyword.

This approach gives you an extremely relevant and useful list of words and phrases to use in your content to help boost your search engine visibility. Here’s a simple example where we ran the term “digital marketing’ through the Related Phrases endpoint to retrieve a list of semantically related terms. Below is a sample of the terms returned;


Related phrases example output

Try it yourself: Use our NLP powered Related Phrases endpoint

However these days it’s not all about keywords.

Semantic Keyword Research

The search engine experience has improved immensely in recent times. Search Engines no longer rely on simple keyword matching and since the introduction of Panda and Penguin by Google they now aim to understand exactly what you are searching for and about.

You can read more about that here: What is Semantic Search?

With these developments in mind, it’s important for marketers to build more meaningful keyword lists or databases that are rich in context and take the searchers intent into account. So how can Text Analysis help us to optimize our content for Semantic Search?

Mining popular content to source target keywords and concepts that are related to your business is an excellent way to start building a semantic rich keyword or even better topic list.

Read about how to do that here: How to do Semantic Keyword Research Using NLP and Text Analysis


2. Content Marketing

Content Creation

Creating quality content that our target market value is more important now than ever before. Good content marketing doesn’t come without its fair share of challenges; knowing your target audience, staying on top of trends, analyzing what works and what doesn’t and positioning yourself as thought leader in your space.

Popular blogs or industry focused outlets can be an excellent source for content ideas. Competitors’ blogs can be an even better source of inspiration on what to do, or sometimes what not to do when creating content for a specific audience.

Analyzing content can help you gain some useful insights into what your target market want to read about. But it takes a lot of time, right?

Not always. By leveraging Text Analysis techniques, analyzing content at scale can be done quite easily. It’s easier than ever before to take a large selection of content and do the following:

  • Automatically summarize posts
  • Extract key Entities (people, places, brands etc) & Concepts from blogs
  • Generate keywords
  • Identify themes

With this information at hand it’s a lot easier to brainstorm content ideas, track competitors content strategies and uncover mentions of brands and people even that are relevant to you.

Check out our previous post: How to analyze your competitor’s content in just 10 minutes with our Google Sheets Add-on


Bonus feature: Hashtag suggestion

A neat little feature we offer at AYLIEN  is Hashtag Suggestion. We don’t need to go into too much detail here as it does exactly what the title suggests, but it’s worth noting as it is another process that can be semi or fully automated to speed up your content efforts.


Content Curation

With the ever-increasing explosion of online content, the need for specific, customized content curation has never been greater. Manually searching through countless social networks and news feeds to find relevant content can be extremely time consuming and is simply not sustainable.

As marketers we want this relevant content delivered to us in real-time, as soon as it is published, without having to manually search for it or simply hope it appears on our social feeds.

There are lots of content aggregators out there, some better than others of course and what you may not know is, Text Analysis and NLP is at the heart of what powers these content analysis tools. It’s now easier than ever before to monitor more than just keywords we can track content based on a number of parameters:

  • Entities mentioned (people, places, organizations etc)
  • Language
  • Category
  • Writer sentiment (positive or negatively written)
  • Source
  • Relevancy
  • Social media performance

Here’s a couple of examples using our own content analysis API;

Positive stories about Tesla that don’t mention SpaceX, written in English and published in the past 30 days. See the results

Negative stories about Donald Trump published in the past 24 hours sorted by the most popular on Facebook. See the results

You can learn more about sourcing and analyzing specific news contenthere to help take your content curation efforts to the next level.


3. Social Listening

Social listening is the process of locating and assessing what is being said about specific brands, people, products and topics on social media.

Marketers can build better campaigns and manage their brand’s online presence and reputation if they can better understand the voice of their customers.

Gathering information from the places where your customers, target audience and competitors participate in online discussion can be invaluable. However, trying to trawl through all of this content manually just isn’t possible.

Text Analytics can make this a lot easier. Advancements in how machines now understand text means we can mine large volumes of user generated content to look for insights at massive scale.



The simplest form of social listening is monitoring mentions of keywords. This is pretty straightforward and can be really useful when used properly.

By leveraging NL
P however you can go beyond keywords and get a bit smarter in what you uncover in social data.

For example, imagine we’re a retail brand with various branches in a variety of locations. By getting a bit smarter and leveraging the ability to extract entities (People, Organizations, Locations etc…) from social data, we can uncover a lot more about perception of our brand online. Automatically, we can uncover what other brands are mentioned alongside ours, are there particular locations mentioned with our brand and so on, all without having to know what we’re looking for.


Sentiment Analysis

Sentiment Analysis is a well known and well documented feature of Text Analysis. Analyzing sentiment determines whether a piece of text is written in a positive, negative or neutral way.

This can be extremely useful in establishing customer sentiment towards a specific brand or product.

Check out Super Bowl 50 according to Twitter: How we analyzed 1.8 million tweets to uncover trends in public opinion during Super Bowl 50


Being able to dive into public opinion towards an event or brand to look for trends or insights helps marketers understand the strengths and weaknesses of their campaigns and the voice of their customers.


Aspect-Based Sentiment Analysis

Aspect-based Sentiment Analysis (ABSA) dives a little deeper by analyzing sentiment towards industry-specific aspects, or topics.

Let’s use a hotel as an example. There are many areas of a hotel that a customer could either praise or complain about in online reviews – food, drinks, amenities, beds, staff, value, view and so on. Using ABSA we can determine sentiment at scale toward each individual aspect. This helps to give an overall view of hotel performance while pinpointing strengths and weaknesses. The graph below shows the sentiment towards the various aspects of a hotel. We can clearly see that their strongest area is food & drink while their weakest is perceived value among customers.



Example of aspect-based approach to analyzing reviews


Read more about ABSA here: Analyzing 500 hotel reviews from Yelp using Aspect-Based Sentiment Analysis


Bonus feature: Generating leads

A great way to locate new business opportunities is to monitor specific phrases and words that describe the needs and/or pain points of your target audience. You can monitor for specific words or phrases that include your competitors brand or product name as well as terms like can’t, won’t, hate, worst, etc. You can also monitor for negative mentions of your competitors, again using Sentiment Analysis. Many organizations and larger brands have specific support or help accounts on the likes of Twitter that make mining this data so easy.

Check out a blog one of our users wrote: How to get actionable leads from Twitter in real time



While we have only really scratched the surface here in terms of how Text Analysis can help marketers, our main goal was to give you an overview of what is possible and to hopefully get those creative juices flowing!

We have thousands of marketers using our Text Analysis API, News API and Google Sheets Add-on to improve their campaigns, monitor their competitors and boost brand awareness & reputation. They come to us with an idea and we show them how we can help them accomplish it.

Not technical? No problem! Our Google Sheets Add-on gives you access to our powerful Text Analysis features within Google Sheets. No programming knowledge required!


Text Analysis API - Sign up




Our Dublin office has been a little quieter than usual this week as we’ve been clocking up the airmiles with trips to the US and Belgium. Our founder & CEO, Parsa, has been stateside meeting customers and speaking at both the Re-Work Deep Learning Summit in Boston and Text by the Bay in San Francisco. Parsa was introducing byte2vec: a flexible embedding model constructed from bytes. More on that to follow!

On Tuesday our VP of Sales & Marketing, Mike Waldron, visited our European neighbours Belgium to attend the Language Technology Industry Summit, organized by LT-Innovate, and to proudly accept their annual award distinguishing “The Best in Language Technology”.

About LT-Innovate

LT-Innovate is the Language Technology Industry Association. Based in Brussels, Belgium, their main objectives are;

  • to strengthen the Language Technology Industry for increased competitiveness in the global markets;
  • to promote language technologies as drivers of economic success, societal well-being and cultural integrity;
  • to encourage collaboration within the Industry and with other stakeholders of the Language Technology value-chains;
  • to articulate the Industry’s collective interests vis-à-vis buyers, researchers, investors and policy makers.

The Language Technology Industry Summit

The LT Industry Summit is the yearly point of convergence between the Language Technology Industry, its clients, research partners and policy makers.



Day 1 kicked off on Tuesday with a welcoming message from Philippe Wacker, secretary general of LT-Innovate. The discussions throughout the day ranged from project war stories from the likes of SDL and Phillips to product showcases from startups and Machine Translation (MT) giants. Topics focused around MT challenges, the rebirth of AI and language technologies in healthcare.

Day 2 is still in full flow taking a slightly different approach in having longer sessions which are split into two separate tracks. Text Analytics has featured heavily today and there are more technology showcases lined up for this afternoon following a great discussion on the challenges of multilingual media publishing.

The Award

The LT-Innovate Award was established in 2012 and distinguishes “The Best in Language Technology”. The LTI Board of Directors evaluate and select two winners each year from a list of nominated organizations based on the following criteria;

  • Innovation & technological excellence
  • Business potential
  • Investment or partnering interest

The award is given at the annual Language Technology Industry Summit in Brussels and we were thrilled to attend in 2016 as proud winners.



Receiving an award like this is a fantastic compliment for the excellent work our brilliant engineers and researchers do everyday. It’s amazing to be recognized by some of the leading Language Technology professionals in Europe for the work we do in the NLP space.

We’d like to extend our thanks to the LT-Innovate board for considering our work at AYLIEN to be among the best in Language Technology. We’re excited about continuing our relationship with the LT-Innovate team and returning to the summit next year.

Wanna try our award-winning API’s?

Click the image below for FREE access to our Text Analysis API or check out our recently released News API.

Happy Hacking!


Text Analysis API - Sign up



As you may be aware, we recently boosted our Text Analysis API offering with a cool new feature, Aspect-Based Sentiment Analysis. The whole idea behind Aspect-Based Sentiment Analysis (ABSA) is to provide a way for our users to extract specific aspects from a piece of text and determine the sentiment towards each aspect individually. Our customers use it to analyze reviews, Facebook comments, tweets and customer feedback forms to determine not just the sentiment of the overall text but what, in particular, the author likes or dislikes from that text

We’ve built models for 4 different domains (industries). You can see the domains and the domain specific aspects listed in the image below.



Not familiar with Sentiment Analysis? We explain it quickly and simply here to help get you up to speed. You can also try it for yourself with our easy-to-use online Demo.

ABSA for the AYLIEN Google Sheets Add-on

We’ve just added the ABSA features to our Google Sheets Add-on. The add-on enables users to perform Text Analysis functions from within Google Sheets, without any coding/programming knowledge. We designed the add-on to be as simple and user friendly as possible. If you are in any way familiar with Google Sheets (or Microsoft Excel), you’ll be up and running in no-time.

It’s so simple, in fact, that we can analyze the sentiment of text (hotel reviews in this instance) in under 15 seconds.

Analyzing hotel reviews from Yelp

To showcase our latest feature addition, we analyzed 500 hotel reviews, from Yelp, within Google Sheets. We’ve embedded the sheet we used below to show you exactly how the add-on functions. 


After running Aspect-Based Sentiment Analysis on the 500 hotels reviews, we had an abundance of data and information to draw insights from. As you can see from the “Analyzed Reviews” sheet in the embedded spreadsheet below, the results of our analysis are laid out neatly in columns containing the review text, the review rating (out of 5) and the positive, negative and neutral aspects found within each review.

Looking beyond the overall sentiment of a review tells us what exactly the customer liked or disliked about their experience. It allows a much greater understanding for the voice of the customer.

Aspects Mentioned

The first thing we wanted to figure out was what aspects the reviewers were speaking about across all reviews and how often each aspect was mentioned.



It’s interesting how little WiFi is mentioned in reviews when it can, in our opinion, be one of the more frustrating aspects of a hotel’s service. It’s also pretty clear from the graph that people are most opinionated about a hotel’s location and the amenities of their room (TV, Iron, mini bar etc…).

World Cloud

We used another simple Sheets Add-on, Word Cloud Generator, to produce word clouds from the most cited positive and negative aspects. Straight away we can see that the two biggest complaints among customers are the room itself and hotel amenities.


Sentiment per Aspect

 Having understood what it is people talk about in reviews we also wanted to dive into the opinion towards each aspect across all the reviews.

To do this we generated aspect-specific pie charts to generate more targeted visualizations (You can see interactive versions in the “Graphs” sheet above).

Note: It’s important to keep in mind the percentages shown are based on the reviews that mention that particular aspect. So taking WiFi, for example, 45.9% of reviews that mentioned this aspect were negative.



Analyzing reviews on a per aspect basis enables hotel management, for example, to focus on and track the performance of specific aspects, departments or services, such as food & beverage or how the staff are perceived by guests. It can also help to uncover correlations between certain aspects – does an increase in positive sentiment toward Staff lead to an increase in positive sentiment towards Value?

Sentiment of Aspects

The last thing we want to do was to try and get a high level overview of the entire collection of reviews. The graph we created below gives a really nice overview and comparison of customer sentiment towards each of the various aspects across all reviews. It gives a snapshot view of hotel performance as a whole according to all of the reviews.


We’re really excited about this latest addition to our Text Analysis API and Google Sheets Add-on. The analysis we performed above really was so simple that we believe anyone can do the same with their own text/data.

Wanna try it for yourself? You can access the AYLIEN Google Sheets Add-on for free and we’ll even give you 1,000 credits free to run your own analysis.

If you want to explore ABSA a bit deeper (and 12 other Text Analysis features) you can sign-up for our Text Analysis API which will enable you to make up to 1,000 API calls per day. No credit card required. Click the image below to get started!


Text Analysis API - Sign up


Last month we launched our latest service offering, our News API. Powered by our Text Analysis Engine, the News API enables users to search and source enriched news and media content from around the Web, in real-time, to help understand content at scale while extracting the data that matters most to you. Our News API launch was featured on Tech Crunch – check it out!

We love creating new things here at AYLIEN. Sometimes we build big kick-ass products like our Text Analysis and News APIs, and sometimes we create smaller (but still kick-ass!) things like useful code snippets for our users, custom integrations, and of course coffee. We create lots of coffee 🙂

But no matter what we are building, there is one mantra that we never stray from, and that mantra revolves around Developer Experience. We understand how frustrating it can be working with poorly documented APIs and we know how important “time to first hello world” (TTFHW) is, therefore we strive to make our APIs as accessible and as easy-to-use as possible, and this is why tens of thousands of developers use our products to enrich their apps and projects.

To achieve this, our APIs needs to be easy to use, easy to integrate with, and be backed up with the support of clear and simple documentation.

Just like our Text Analysis API, we want our News API to be all of the following;

  • Simple
  • Hackable
  • Self-service
  • Developer-focused
  • Reliable & consistent

With this is mind we are today bringing you SDKs for 7 popular coding languages, each with complete documentation so you can get up and running in no time. Visit our GitHub repo’s at the links below to download your SDK of choice.



Python SDK  Go SDK  C# SDK


We are already starting to see some really cool user-created apps and projects using our News API. Stay tuned as we will be sharing the best of them right here on our blog and social media channels. If you have created something using our API, whether big or small, we would love to hear about it 🙂

Happy Hacking!

News API - Sign up