.NET Text & Documents Classification API

Empower your .NET applications with File & Text Classifier abilities using pre-defined tags or categories within IAB-2, Documents and Sentiment taxonomies.

Download Free Trial

Text sentiment analysis and text classification are two powerful technologies that can be used to extract meaningful insights from unstructured textual data and have numerous practical applications in various industries. These techniques can be applied in a wide range of use cases, from social media monitoring to customer feedback analysis, to categorizing news articles, to detecting spam emails, and much more.

Sentiment analysis is the process of identifying the emotional tone of a piece of text. The goal of sentiment analysis is to extract subjective information from text to understand the author’s opinion or emotional state. This technology can be applied to social media monitoring, customer feedback analysis, brand reputation management, and much more to classify feedback or mentions into positive, negative, or neutral categories.

Text classification is the process of categorizing text into predefined classes or categories. This technology can be used to organize large collections of text documents or to filter out irrelevant information from a stream of text data. Text classification can be based on different criteria, such as semantics, sentiment, or IAB (Interactive Advertising Bureau) categories. IAB-based classification is used to categorize text based on the IAB categories. This approach is often used in advertising to classify content for ad targeting. For example, a software developer may use IAB-based classification to classify website content into different categories, such as arts and entertainment, health and fitness, or travel.

Document categorization is a common use case for text classification that involves organizing documents into different categories based on their content. This can be useful in various industries, such as legal, finance, and healthcare, where there is a large amount of unstructured data that needs to be organized and analyzed. One way to implement document categorization is to use GroupDocs.Classification, a powerful text classification library that supports a wide range of document formats, including PDF, DOC, DOCX, RTF, and TXT. Our solution is built on top of machine learning algorithms that make it highly accurate and reliable, allowing you to make smarter decisions based on your text data. As a software developer, you can use text sentiment analysis and text classification to create a wide range of applications like a social media monitoring tool that tracks brand mentions and categorizes them by sentiment, a news aggregator that categorizes articles by topic, a spam email filter that uses text classification to identify and filter out spam emails or extract other meaningful insights from unstructured textual data and build applications that provide value to users.

One of the best features of GroupDocs.Classification is its flexibility. This means that you can classify text with almost any type of document. Another great feature of GroupDocs.Classification is its user-friendly API. With just a few lines of code, you can integrate our library into your own application and start classifying text right away. Our API is easy to use and well-documented, so you can get up and running in no time. By using GroupDocs.Classification for document categorization, businesses can save time and resources by automating the process of organizing and analyzing their documents. This can lead to more efficient workflows, better decision-making, and ultimately, improved business outcomes.

Advanced Text & Documents Classification API Features

Precise Document Classification

GroupDocs.Classification API supports classification for a variety of document formats. The below C# code example shows how to classify a PDF file from the current folder with Documents taxonomy by returning 3 best results.

// Initialize general-purpose classifier (IAB-2, Documents, Sentiment Analysis).
var classifier = new GroupDocs.Classification.Classifier();

// Classify pdf file with Documents taxonomy and return the 3 most likely categories.
var response = classifier.Classify("document.pdf", ".", 3, Taxonomy.Documents);
Console.WriteLine($"{response.BestClassName}: {response.BestClassProbability}");

Precise Text Classification

GroupDocs.Classification API also supports text classification. Text classification can be performed with 4 different taxonomies: IAB-2, Documents, Sentiment, and Sentiment3. The below C# code example shows how to classify text with the default (IAB-2) taxonomy by returning the best result.

// Initialize general-purpose classifier (IAB-2, Documents, Sentiment Analysis).
var classifier = new GroupDocs.Classification.Classifier();

// Classify text with IAB-2 taxonomy and return the the best category.
var response = classifier.Classify("Classify text using the default IAB-2 taxonomy");
Console.WriteLine($"{response.BestClassName}: {response.BestClassProbability}");

Precise Multilingual Sentiment Analysis

GroupDocs.Classification for .NET allows to perform cross-domain Sentiment Analysis (Classification) in English, Chinese, Spanish, and German. GroupDocs.Classification for .NET will detect the proper language(s) automatically. Sentiment analysis API use cases are illustrated by the following C# code:

// Initialize cross-domain multilingual sentiment classifier. 
// SentimentClassifier supports multilingual classification with English, Chinese, Spanish, and German.
var classifier = new GroupDocs.Classification.SentimentClassifier();

// Sentiment analysis of the English text.
var response = classifier.Classify("Experience is simply the name we give our mistakes");
Console.WriteLine($"{response.BestClassName}: {response.BestClassProbability}");

// Sentiment analysis of the Chinese text with the same classifier and Sentiment3 (Negative/Neutral/Positive) taxonomy.
response = classifier.Classify("熟能生巧", taxonomy: Taxonomy.Sentiment3);
Console.WriteLine($"{response.BestClassName}: {response.BestClassProbability}");

Support and Learning Resources

Back to top