# bfelbo/DeepMoji

State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.

Repository: https://github.com/bfelbo/DeepMoji
Canonical: https://ross.abutalabs.com/products/deepmoji
Homepage: https://deepmoji.mit.edu/
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, deep-learning, natural-language-processing, python, ai, keras, neural-networks, nlp, sentiment-analysis, tensorflow, text-classification
Last push: 2024-08-02T16:13:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3333, "days_push": 761, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1554, forks 307 (observed 2026-08-28T04:05:02.984075+00:00)

## What it is
DeepMoji is a deep learning model trained on 1.2 billion tweets with emojis to understand emotional language, with code for scoring texts, encoding emotional feature vectors, and transfer learning. It is built on Keras with Theano or TensorFlow backends.

## Use cases
- predict emojis for a piece of text
- analyze sentiment and emotion in tweets
- detect sarcasm in text
- extract emotional feature vectors from text
- fine-tune a pretrained model on a new emotion-related dataset

## When to choose
- you need emotion or sarcasm analysis for short social media text
- you want a pretrained model for transfer learning on emotion-related NLP tasks
- you work in Python with Keras/TensorFlow

## When to avoid
- you need a maintained Python 3 codebase out of the box
- you prefer PyTorch (use torchMoji instead)
- you need production-grade sentiment analysis for long-form or non-social-media text

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: sentiment-analysis, emotion-detection, transfer-learning, emojis, text-classification, keras, tensorflow, natural-language-processing

## Member repositories
- bfelbo/DeepMoji (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:02.984075+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:04.723298+00:00, confidence not recorded.
  - readme: https://github.com/bfelbo/DeepMoji (fetched 2026-08-28T04:05:02.984075+00:00, sha a619eec359da)
- Data as of 2026-08-30T08:39:29.467469+00:00.