Senta
Sentiment analysis toolkit
An open-source sentiment analysis system that provides pre-trained models and tools for text classification, aspect-level sentiment analysis, and opinion extraction.
Baidu's open-source Sentiment Analysis System.
2k stars
62 watching
368 forks
Language: Python
last commit: 7 months ago aspect-level-sentimentnatural-language-processingopinion-target-extractionpaddlepaddlesentiment-analysissentiment-classification
Related projects:
Repository | Description | Stars |
---|---|---|
| An algorithmic tool for analyzing sentiment in text with support for nuanced handling of linguistic features. | 20 |
| Analyzes sentiment in Thai text using machine learning algorithms and natural language processing techniques. | 12 |
| A sentiment analysis tool for Hungarian language with REST API and Docker container support | 11 |
| Analyzes opinions expressed on various aspects of entities in Hindi reviews to provide granular sentiment recommendations | 11 |
| A minimal sentiment analyzer written in CoffeeScript for the browser. | 38 |
| An NLP microservice for analyzing the sentiment of user input | 6 |
| A tool for analyzing the sentiment of Hungarian news articles based on word embeddings and dictionaries. | 1 |
| A sentiment analysis tool trained on the Stanford Sentiment Treebank using various neural network architectures. | 367 |
| An application demonstrating sentiment polarity analysis using CoreML and Swift. | 119 |
| Analyze sentiment in text using a pre-defined lexicon of words with their associated emotional connotations. | 10 |
| An application that uses natural language processing to determine the sentiment behind user-generated text data | 52 |
| Provides a simple sentiment analysis tool with extensible analysis strategies | 14 |
| An open source Swift library for sentiment analysis of phrases using word lists and emoji rankings. | 13 |
| A Python library providing an API for sentiment analysis of Polish text using deep learning and Word2vec models | 27 |
| Detects sentiment in short pieces of text using a pre-trained BERT model fine-tuned on the IBM Claims Dataset. | 58 |