Contextual data? hyScore.io! One API for several use cases.
You want to perform a contextual keyword extraction, a contextual or sentiment analysis? With our lean RESTful-API approach it is simple. Below you’ll find a list of the hyScore API feature set.
Find some inspiration! Monetization? Content optimization? Take a look at our use case section of how you can use our service to drive your business.
We’re multi lingual
18 languages (and counting) are actually supported by our contextual data analysis API service:
- Chinese (CN)
- Czech (CZ)
- Dansk (DK)
- Dutch (NL)
- English (EN)
- Finnish (FI)
- French (FR)
- German (DE)
- Hindi (IN)
- Hungarian (HU)
- Italien (IT)
- Norwegian (NO)
- Polish (PL)
- Portuguese (PT)
- Russian (RU)
- Spanish (ES)
- Swedish (SE)
- Turkish (TR)
- more to follow…
All languages are detected automatically by the algorithms and the language information will be provided as result within the JSON response. If we don’t support a language the system always fall back to English (EN) language.
Contextual keyword extraction – scored and weighted
By “magic” our sophisticated deep learning algorithms are extracting the most valuable keywords scored and weighted in a contextual manner. The algorithms analyze the context of an URL/Text and provide a list of weighted keywords which are reflecting the meaning of the whole e.g. article. Based on this JSON response you can do other valuable stuff for your own purpose. Please take a look at our use-cases section. It’s worth it!
Keyword frequency & Entities
As additional information, we provide the number (count) of how often the keyword was found within the requested URL / text. A keyword with a high frequency is not automatically the highest weighted keyword. Besides the frequency, we show you the determined entity of the keyword. Is a person? a place? a band? a country? Whatever…
Sentiment analysis involves evaluating online opinions based on specific words. The sentiment is then judged to be positive, negative or neutral. To put it simply, “I got a great deal at X Store!” would count toward positive sentiment, while, “X Store just ripped me off for the last time!” would go in the negative column. A neutral comment might be, “An X Store just moved into the neighborhood. I think I’ll go check it out on my lunch break.” However, it’s not always that simplistic. There are many shades and levels of sentiment to consider, and a single article, news, tweet or post can contain several. We express the sentiment with a score value in the JSON response. Currently available in German (DE) and English (EN). More languages will be supported step-by-step.
The system returns optional the determined text of the URL we’ve analyzed in the JSON response. If mandatory (for some reason) you get the information for further analysis.
The system returns weighted the categories of the website in the JSON response. News, Entertainment, Education, Politics, you name it. There are plenty of categories available. This information is part of the standard response.
IAB content taxonomy
The system returns by default the IAB content taxonomy and IAB code of the website URL in the JSON response. Contextual taxonomy was developed by IAB in consultation with taxonomy experts from academia, ad measurement companies, and members of the IAB Networks & Exchanges Committee. This taxonomy defines contextual content categories on at least three different tiers. The “IAB Tech Lab Content Taxonomy” was previously called the “Quality Assurance Guidelines (QAG) Taxonomy.”
Custom identifier and data pass-back
With the request to our API, you can pass any kind of custom identifier (cookie ID, Login ID, Advertising or Device ID, any identifier you want…) or custom data as a string. This enables you to pass through a custom identifier to enrich user profiles for your own or 3rd party DMP and create your own target group segments. In addition, this allows you to personalize applications, services or content (recommendation) for a single user.
We’re platform independent
Come on… it’s a simple RESTtful API. You can use hyScore for any kind of web application, any mobile application, any platform – stop – as long you can send a POST request to our API service and handle the JSON response.
Scalable, reliable and fast as hell
We are on reducing the latency to a minimum to provide the keywords as fast as hell. Actually, we measure in average a response time between ~65 and 110ms (average: 86ms) depending on the involved networks, the websites latency/size, and other parties. We’re sure to lower that response time and performance indicator step-by-step to be “fast as hell”. We can try to go even faster to provide our information for your real-time cases. Please get in contact with us if there is a need for your specific business case.
RESTful API & Configurable JSON output
We are developer friendly and provide an easy method to integrate our service. Connect your application, website or any other 3rd party system via RESTful-API. Find more details in our documentation…
You can configure how the JSON result should look like. Do you want the top three keywords or just all keywords the hyScore system extracted out of your URL/Text? Please look at our hyScore API documentation .
Our API is SSL(Secure Sockets Layer) secured. SSL is a standard security technology for establishing an encrypted link between a server and a client—typically a web server (website) and a browser or any other software/system. SSL allows sensitive information such as credit card numbers, social security numbers, and login credentials to be transmitted securely. Normally, data sent between browsers and web servers is sent in plain text – leaving you vulnerable to eavesdropping. If an attacker is able to intercept all data being sent between a browser and a web server, they can see and use that information. We use SSL for our hyScore RestfulAPI and the communication is secure.
Unlimited trial period
We want you to test our service. Not in a hurry. You should take your time during the integration phase. So you have an amount of 10.000 requests/month for free. If you need more – contact us. We’ll find a way.
To keep our service up and running we have a simple, volume based and transparent billing method. Our pricing model is easy to understand. We’ll start for free (limited to 10.000 requests / per month) and then we’ll charge a technical CPM for any additional API-Call. You’ll get a detailed report of the requests you’ve made at the end of the month.
Simple rule: As higher the volume of API-calls, the lower the cost per request. Don’t hesitate to ask us for an individual offer until the subscription plans are available.
If you’ve any additional questions please get in touch with us!