#202202nd of 206 in ML frameworks and libraries
vadersentiment
Rule-based sentiment scorer for short social media text, in Python
- Stars
- 5.1k
- License
- MIT
- Last commit
- Mar 2026
- Last release
- Nov 2014
- Language
- Python
4,947 on 22 Apr 20265,096 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
VADER is a Python library that scores text sentiment using a human-rated lexicon of about 7,500 tokens plus grammatical rules for negation, punctuation, ALL CAPS, degree modifiers and emoticons. SentimentIntensityAnalyzer.polarity_scores() returns pos, neu, neg and a normalized compound score from -1 to +1. It needs no training and runs on CPU; the repo also ships the rated tweet, NYT, movie and Amazon datasets.
Who it is for: Python developers needing English sentiment scores for short or social text
Strengths
- Installs with pip install vaderSentiment; no model download or training step
- Handles negation, punctuation, capitalization, slang, emoticons and emoji via explicit rules
- Lexicon rated by 10 human raters; ground-truth datasets included for evaluation
- Linear-time scoring after the O(N^4) to O(N) refactor; already part of NLTK
Weaknesses
- English only; non-English text must be translated first, and the demo relies on an external service
- Lexicon and rules, not a learned model, so context and sarcasm are missed
- Last tagged release is 2014-11-17, so version history is stale
- Returns sentence-level scores only; longer texts need external sentence splitting such as NLTK
What it needs
- no GPU
- Needs NLTK and requests (demo only), MyMemory Translation Service (demo only)
- Models: vader_lexicon.txt rule-based lexicon
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 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 |