#122122nd of 168 in ML frameworks and libraries
textblob
Python library for part-of-speech tagging, sentiment and noun phrase extraction
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 9.6k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Sep 2013
- Language
- Python
9,466 on 21 Apr 20269,555 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
TextBlob is a Python library that wraps NLTK and pattern behind a small API for classic NLP tasks. It covers part-of-speech tagging, noun phrase extraction, sentiment polarity, Naive Bayes and Decision Tree classification, tokenization, n-grams, lemmatization, spelling correction and WordNet lookups. It is a rule- and statistics-based toolkit, not an LLM library.
Who it is for: Python developers needing simple text analysis without training neural models
Strengths
- Small API: a TextBlob object exposes tags, noun_phrases, sentences and sentiment as attributes
- Installs with pip; no model server or database needed
- Tagging, sentiment, classification, n-grams, inflection and spelling correction in one package
- MIT licensed; new models or languages can be added through extensions
Weaknesses
- Built on NLTK and pattern, so accuracy is limited to classic non-neural methods
- Needs a separate corpora download step after pip install
- README describes no LLM, embedding or transformer support
- Last tagged release is 2013-09-26, though commits continue
What it needs
- no GPU
- Needs NLTK, pattern, NLTK corpora (python -m textblob.download_corpora)
- Models: Naive Bayes classifier, Decision Tree classifier
Quick answers
Is textblob open source?
Yes. Its code is on GitHub under the MIT license.
Does textblob need a GPU?
No, it runs without one.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |