The Bitext API is a suite of multilingual semantic services designed specifically for the needs of clients who offer solutions processing user-generated content such as customer experience management tools or voice of the customer analytics. Currently four semantic services are available: entity and concept extraction, sentiment analysis and text categorisation.

The Bitext API has been developed over 4 years by a team of highly experienced computational linguists and computer scientists. The semantic services are based on natural language processing (NLP) which has been built entirely from the ground up by Bitext. The system works using rule-based techniques for morphological, syntactic and semantic analysis.

The semantic services have been developed for 10 languages: English, Spanish, French, Portuguese, Italian, German, Dutch, Catalan, Galician and Basque. Of these English, Spanish, Portuguese, Italian, French and German are currently available (July 2013) via our web service API. The other languages will also soon be available via the web service API.

Sentiment Analysis

Sentiment analysis that delivers more than just positive or negative valuations with built-in sentiment scoring, topic identification and categorisation.

The sentiment analysis service is built using our NaturalOpinions technology. A live demo of this service updated on daily basis can be seen for English and for Spanish.

The purpose of this service is to extract opinions from text. An opinion represents the subject an author is writing about and a sentiment score that classifies how positively or negatively the author feels towards that subject. Deep Linguistic Analysis is used to identify the subject the author is discussing. This can be:

  • an entity (brand/ person/product/place…
  • a concept (like “global warming”, “public policies” or “financial crisis”).

The sentiment analysis service will also break the opinion down to detect exactly which features or attributes or elements of the subject are being discussed. For a product this could be the main components or accessories as for example, the “screen“ in “the screen of the Galaxy Tab” or the “case“ in “my new iPad case“. For a person this could be the activities or attitudes associated with them. For a place it could be the specific buildings or institutions located there. Examples of the kinds of features that are extracted can be seen in our live demo.

When combined with our categorisation service these features or attributes can be used to place the opinion in a category taken from a taxonomy. This provides a powerful way to structure a set of texts according to what topics people are discussing and how they feel about those topics. An example of this can be seen in our live demo.

Sentiment scores are also based on Deep Linguistic Analysis. The more intense the feelings of the author about the subject, the higher or lower the score. To achieve this, the analysis detects linguistic features such as the strength of the vocabulary or the use of intensifiers like “really”, “very” or “extremely”. So a comment like “Installing software on this machine is painful!” will be scored as less negative than “Installing software on this machine is really very painful indeed!”

Deep Linguistic Analysis accurately handles complex issues like negation: “the new Nikon is really not bad at all”.

The service handles complex linguistic issues that play a major role in sentiment analysis, such as negation or comparative sentences. Deep Linguistic Analysis automatically handles this type of phenomena capturing the difference between opinions like:

  • “This phone is much better than my old phone.” – Positive
  • “This phone is not much better than my old phone.” – Negative

The sentiment analysis service is not limited to extracting a single opinion per sentence. It actually detects as many opinions as the sentence contains. For example in the sentence “This phone is awesome, but it was much too expensive and the screen is not big enough” three opinions will be extracted: “phone” + “awesome”, “phone” + “much too expensive” and “screen” + “not big enough”.

If you would like to try our API, please ask for a user account.

Just remember that, in addition to Sentiment analysis, the following services are also available:

  • Entity extraction
  • Concept extraction
  • Text categorisation
Last 7 days, UTC

Average Latency

Average Uptime

Current Status

  • No information
  • Outage
  • Disruption
  • Normal
Average latency determined from Mashape to API Response time
Query Authentication

The username & password










HTTP 200 : Data POST/WS_NOps_Val/Service.aspx
Listing of sentences from the input text.
  "data": [
      "id": 1,
      "text": "This is a sentence I like",
      "global_value": 2,
      "details": [
          "valuables_norm": "SENTENCE",
          "valuers_norm": "LIKE",
          "value": 2

Test console

The language of the text to be analysed e.g. one of Eng, Esp, Por, Ita, Deu or Fra
Example: Eng




The user-defined ID of the request
Example: 1




The output format of the response. One of JSON, XML or CSV
Example: JSON




Whether to normalize terms in the response. One of Yes or No
Example: Yes




The text to be analysed
Example: This is a sentence I like



Consume this API completely for free!

By joining the mashape API marketplace you can start using Bitext Sentiment Analysis API today!

Login to your account or signup: Create Account

   Signup with GitHub

By signing up you agree to our terms of service.