# baidu/Senta

Baidu's open-source Sentiment Analysis System.

Repository: https://github.com/baidu/Senta
Canonical: https://ross.abutalabs.com/products/senta
Language: Python
License: Apache-2.0
License Family: permissive
Topics: natural-language-processing, sentiment-analysis, sentiment-classification, paddlepaddle, aspect-level-sentiment, opinion-target-extraction
Last push: 2024-08-20T16:16:48+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": 2984, "days_push": 743, "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 2015, forks 363 (observed 2026-08-28T04:06:05.500771+00:00)

## What it is
Senta is Baidu's open-source sentiment analysis system built on the SKEP (Sentiment Knowledge Enhanced Pre-training) model. It provides pretrained Chinese and English models and one-click tools for sentence-level sentiment classification, aspect-level sentiment classification, and opinion extraction.

## Use cases
- classify sentiment of product reviews
- run aspect-based sentiment analysis on Chinese text
- extract opinion targets from reviews
- fine-tune a sentiment pretrained model with SKEP
- deploy a one-click sentiment prediction pipeline
- reproduce ACL 2020 SKEP benchmark results

## When to choose
- you need state-of-the-art sentiment analysis for Chinese or English text
- you want pretrained sentiment models with minimal code
- you need aspect-level sentiment classification or opinion extraction
- your stack already uses PaddlePaddle

## When to avoid
- you need a PyTorch or TensorFlow-native solution
- you need general-purpose NLP beyond sentiment tasks
- you require actively evolving features, as development has slowed to maintenance

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: sentiment-analysis, sentiment-classification, skep, paddlepaddle, aspect-level-sentiment, opinion-target-extraction, pretrained-models, chinese-nlp, natural-language-processing, linux

## Member repositories
- baidu/Senta (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:05.500771+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 2026-08-30T03:00:43.626766+00:00, confidence not recorded.
  - readme: https://github.com/baidu/Senta (fetched 2026-08-28T04:06:05.500771+00:00, sha 5eab54c7f95f)
  - registry_pypi: https://pypi.org/pypi/senta/json (fetched 2026-08-29T10:40:39.205057+00:00, sha c93a88c91863)
- Data as of 2026-08-30T08:39:29.467469+00:00.