Classification of text is also known as text categorization. Text classifiers can be used to establish, structure, and categorize almost anything in the text. For example, new articles can be prearranged by topics, support tickets can be organized by urgency, discussions can be organized by language and brand mentions can be organized by emotion etc.
GroupDocs.Classification Cloud API enables you to classify your raw text as well as documents ‎into the predefined categories. The Classification Cloud supports multiple taxonomy types, such as IAB-2 ‎taxonomy and Document taxonomy. Classification information can be viewed regarding classes as well ‎as their respective probabilities.

Noticeable Features

• Perform raw text classification as per IAB-2 taxonomy
• Classify documents based on Document taxonomy
• View classes with their respective probabilities as classification information
• Easy integration with REST API
• Secure APIs that require authentication

Supported formats

GroupDocs.Classification Cloud REST API supports the classification of:

• Raw text
• Documents
  • Portable Document Format: PDF
  • Microsoft Word: DOC, DOCX, DOCM, DOT, DOTX, DOTM
  • OpenDocument Formats: ODT, OTT
  • Rich Text Format: RTF
  • Plain Text File: TXT

Raw Text Classification

This API retrieves raw text classification result for IAB-2 taxonomy or Documents taxonomy. It returns an object that contains information about the best class and its probability and about probabilities of the other classes.

Request

curl -v "http://api.groupdocs.com/v1/classification/classify&bestClassesCount=3" 
-H "content-type: application/json"
-X POST -d '{ "Description" : "Medicine is an important part of our life" }'

Response

{
  "bestClassName": "Healthy_Living",
  "bestClassProbability": 53.77,
  "bestResults": [
    {
      "className": "Healthy_Living",
      "classProbability": 53.77
    },
    {
      "className": "Medical_Health",
      "classProbability": 38.27
    },
    {
      "className": "Pets",
      "classProbability": 1.98
    }
  ],
  "code": 200,
  "status": "OK"
}

Documents Classification

GroupDocs.Classification API retrieves document classification result for IAB-2 taxonomy or Documents taxonomy. It returns an object that contains information about the best class and its probability and about probability of other classes. Please click here for further details regarding supported document formats in GroupDocs.Classification Cloud.

Request

curl -v "http://api.groupdocs.com/v1/classification/classify"
-H "content-type: application/json"
-X POST -d '{ "Document": {"Folder": "words/docx","Name": "four-pages.docx" } }'

Response

{
  "bestClassName": "Books_and_Literature",
  "bestClassProbability": 48.92,
  "bestResults": [],
  "code": 200,
  "status": "OK"
}

GroupDocs is the market leader of document manipulation APIs. It provides a wide range of APIs, covering all popular file formats. We are excited to introduce another unique product: GroupDocs.Classification Cloud REST API. It will perform classification to known categories. It will support text and document classification into Interactive Advertising Bureau taxonomy (IAB-2) or Documents taxonomy. The Documents classification is often used in various business processes to automate the flow of documents through the organization. GroupDocs.Classification Cloud REST API is a platform independent REST API, that will allow developers to add document/text classification feature in their applications using a simple set of requests.

Supported formats

GroupDocs.Classification Cloud REST API supports the classification of:

• Raw text
• Documents
  • Portable Document Format: PDF
  • Microsoft Word: DOC, DOCX, DOCM, DOT, DOTX, DOTM
  • OpenDocument Formats: ODT, OTT
  • Rich Text Format: RTF
  • Plain Text File: TXT

Supported Taxonomy

Taxonomy (general) is the practice and science of classification of things or concepts, including the principles that underlie such classification. We will support two taxonomies in the first version:

IAB-2 taxonomy

• Automotive
• Books_and_Literature
• Business_and_Finance
• Careers
• Education
• Events_and_Attractions
• Family_and_Relationships
• Fine_Art
• Food_&_Drink
• Healthy_Living
• Hobbies_&_Interests
• Home_&_Garden
• Medical_Health
• Movies
• Music_and_Audio
• News_and_Politics
• Personal_Finance
• Pets
• Pop_Culture
• Real_Estate
• Religion_&_Spirituality
• Science
• Shopping
• Sports
• Style_&_Fashion
• Technology_&_Computing
• Television
• Travel
• Video_Gaming

Documents taxonomy

• ADVE – advertisements, brochures.
• Email
• Form
• Letter
• Memo – memorandums.
• News – articles, including news articles.
• Invoice
• Report
• Resume
• Scientific – scientific papers.
• Other – the other classes of documents or cases where the classifier is not sure.

Our First Version

We are currently in the process of preparing Examples and Documentation for this new product. We have planned to release the first version of GroupDocs.Classification Cloud REST API soon with features shared above. If you have any questions or suggestions, please feel free to write in groupdocs.cloud Forum.

Please stay tuned to this blog for further updates.