Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Repository with all what is necessary for sentiment analysis and related areas
| Date | Stars |
|---|---|
| 2026-07-24 | 552 |
| 2026-07-25 | 552 |
| 2026-07-28 | 552 |
| 2026-07-30 | 552 |
| 2026-08-06 | 552 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Sentiment Analysis
A curated list of awesome sentiment analysis frameworks, libraries, software (by language), and of course academic papers and methods. In addition NLP lib useful in sentiment analysis. Inspired by awesome-machine-learning.
**Latest Update (July 2026)**: Research refresh covering 2025 through mid-2026 work:
- **NEW: Reasoning Models for Sentiment Analysis** — DeepSeek-R1 evaluation, when reasoning helps vs. hurts (task-complexity study), self-consistent structured generation
- **SemEval-2026 Task 3 (DimABSA)** — dimensional valence-arousal ABSA: task paper, data repository, and a first system paper (SCSG)
- **ABSA** — expanded Arctic-ABSA (Snowflake) entry, ZeroABSA (EMNLP 2025), multilingual ABSA evaluation with two new German datasets incl. the first German ASQP dataset (LREC 2026)
- **Low-resource & cross-lingual** — TriLex lexicon expansion for African languages, Bengali-English cross-lingual sentiment-bias audit
- **Financial SA** — fine-tuned lightweight open LLMs (Qwen3/Llama3 8B) outperforming FinBERT
- **Multimodal** — QA-MoE quality-aware mixture-of-experts for robust multimodal SA
- WASSA 2026 and updated workshop links
Previous update (April 2026) added: LLMs (GPT-4, Claude, Llama, Gemini, Mixtral, DeepSeek), modern transformers (RoBERTa → ModernBERT), multimodal and multilingual methods (Brand24/MMS — NeurIPS 2023), LLM techniques (prompting, CoT, RAG, LoRA/QLoRA, RLHF, DPO), LLM evaluation & benchmarks, explainable SA, LLM reliability & safety, and recent datasets (2023-2026).
If you want to contribute to this list (please do), send me a pull request or contact me [@luk_augustyniak](https://twitter.com/luk_augustyniak)
## Table of Contents
<!-- MarkdownTOC depth=4 -->
- [Libraries](#libraries)
- [Modern Transformer-based Libraries (2023-2026)](#modern-transformer-based-libraries-2023-2026)
- [Traditional Libraries](#traditional-libraries)
- [Aspect-Based Sentiment Analysis](#aspect-based-sentiment-analysis)
- [Resources](#resources)
- [Lexicons](#lexicons)
- [Datasets](#datasets)
- [Classic Benchmarks](#classic-benchmarks)
- [Recent Datasets (2023-2026)](#recent-datasets-2023-2026)
- [Domain-Specific Datasets](#domain-specific-datasets)
- [Word Embeddings](#word-embeddings)
- [Pretrained Language Models](#pretrained-language-models)
- [Large Language Models (2023-2026)](#large-language-models-2023-2026)
- [Encoder-based Transformers (BERT Family)](#encoder-based-transformers-bert-family)
- [Multilingual Transformers](#multilingual-transformers)
- [Domain-Specific Models](#domain-specific-models)
- [Decoder-based Models](#decoder-based-models)
- [Hybrid Pretrained / Multi-paradigm Architectures (2023-2025)](#hybrid-architectures-2023-2025)
- [Multimodal Sentiment Analysis](#multimodal-sentiment-analysis)
- [Overview](#overview)
- [Recent Models and Frameworks (2024-2026)](#recent-models-and-frameworks-2024-2026)
- [Multimodal LLMs for Sentiment Analysis](#multimodal-llms-for-sentiment-analysis)
- [Key Research Findings (2024-2025)](#key-research-findings-2024-2025)
- [Applications](#applications)
- [Multilingual and Cross-lingual Sentiment Analysis](#multilingual-and-cross-lingual-sentiment-analysis)
- [State-of-the-Art Models (2024-2025)](#state-of-the-art-models-2024-2025)
- [Recent Approaches and Techniques](#recent-approaches-and-techniques)
- [Performance Benchmarks](#performance-benchmarks)
- [Supported Languages](#supported-languages)
- [LLM Techniques for Sentiment Analysis](#llm-techniques-for-sentiment-analysis)
- [Prompt Engineering](#prompt-engineering)
- [In-Context Learning & Few-Shot Methods](#in-context-learning--few-shot-methods)
- [Retrieval-Augmented Generation (RAG)](#retrieval-augmented-generation-rag)
- [Parameter-Efficient Fine-Tuning (PEFT)](#parameter-efficient-fine-tuning-peft)
- [Instruction Tuning &Excerpt of 87,758 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f948171fee53be9a, topic:nlp, topic:sentiment-analysis, name:sentiment analysis
