Open Source Sentiment Analysis

Measure opinion and emotion in reviews, social posts and support tickets, from lexicon-based scorers to fine-tuned transformer models.

232
projects
224.8K โ˜…
total stars
+295
stars this week
Python
top language

ranked by GitHub stars ยท updated Nov 12, 2026

๐Ÿ”ฅ Trending this week in Sentiment Analysis

Sentiment Analysis

666ghj/BettaFish

โ–ฒ +78 โ˜… this week

ๅพฎ่ˆ†๏ผšไบบไบบๅฏ็”จ็š„ๅคšAgent่ˆ†ๆƒ…ๅˆ†ๆžๅŠฉๆ‰‹๏ผŒๆ‰“็ ดไฟกๆฏ่Œงๆˆฟ๏ผŒ่ฟ˜ๅŽŸ่ˆ†ๆƒ…ๅŽŸ่ฒŒ๏ผŒ้ข„ๆต‹ๆœชๆฅ่ตฐๅ‘๏ผŒ่พ…ๅŠฉๅ†ณ็ญ–๏ผไปŽ0ๅฎž็Žฐ๏ผŒไธไพ่ต–ไปปไฝ•ๆก†ๆžถใ€‚

๐Ÿง  Natural Language Processing
PythonGPL-2.0updated Oct 16, 2026
GitHub โ†—โ˜… 42.7Kโ‘‚ 7.6K
Sentiment Analysis

QwenAudio/SenseVoice

โ–ฒ +48 โ˜… this week

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

๐ŸŽ™๏ธ Speech Recognition
CMITupdated Sep 30, 2026
GitHub โ†—โ˜… 9.7Kโ‘‚ 848
Sentiment Analysis

scofield7419/THOR-ISA

โ–ฒ +42 โ˜… this week

Codes for ACL 2023 paper: Reasoning Implicit Sentiment with Chain-of-Thought Prompting

PythonApache-2.0updated Aug 28, 2023
GitHub โ†—โ˜… 202โ‘‚ 12
Sentiment Analysis

AI4Finance-Foundation/FinGPT

โ–ฒ +28 โ˜… this week

FinGPT: Open-Source Financial Large Language Models! Revolutionize ๐Ÿ”ฅ We release the trained model on HuggingFace.

๐Ÿค– Language Models๐Ÿง  Natural Language Processing
Jupyter NotebookMITupdated Oct 25, 2026
GitHub โ†—โ˜… 21.6Kโ‘‚ 3.1K
Sentiment Analysis

devaldaki3/CineMatch

โ–ฒ +14 โ˜… this week

Intelligent Movie Recommendation Engine powered by Machine Learning, NLP (Natural Language Processing), and real-time Sentiment Analysis via TMDb API.

๐Ÿง  Natural Language Processing
Jupyter Notebookno licenseupdated Apr 18, 2026
GitHub โ†—โ˜… 128โ‘‚ 0
Sentiment Analysis

PaddlePaddle/PaddleNLP

โ–ฒ +6 โ˜… this week

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

๐Ÿง  Natural Language Processingโ›๏ธ Information Extractionโ“ Question Answering
PythonApache-2.0updated May 23, 2026
GitHub โ†—โ˜… 13Kโ‘‚ 3K

Top 30 sentiment analysis tools by stars

Sentiment Analysis๐Ÿฅ‡#1

666ghj/BettaFish

โ–ฒ +78 โ˜… this week

ๅพฎ่ˆ†๏ผšไบบไบบๅฏ็”จ็š„ๅคšAgent่ˆ†ๆƒ…ๅˆ†ๆžๅŠฉๆ‰‹๏ผŒๆ‰“็ ดไฟกๆฏ่Œงๆˆฟ๏ผŒ่ฟ˜ๅŽŸ่ˆ†ๆƒ…ๅŽŸ่ฒŒ๏ผŒ้ข„ๆต‹ๆœชๆฅ่ตฐๅ‘๏ผŒ่พ…ๅŠฉๅ†ณ็ญ–๏ผไปŽ0ๅฎž็Žฐ๏ผŒไธไพ่ต–ไปปไฝ•ๆก†ๆžถใ€‚

๐Ÿง  Natural Language Processing
PythonGPL-2.0updated Oct 16, 2026
GitHub โ†—โ˜… 42.7Kโ‘‚ 7.6K
Sentiment Analysis๐Ÿฅˆ#2

AI4Finance-Foundation/FinGPT

โ–ฒ +28 โ˜… this week

FinGPT: Open-Source Financial Large Language Models! Revolutionize ๐Ÿ”ฅ We release the trained model on HuggingFace.

๐Ÿค– Language Models๐Ÿง  Natural Language Processing
Jupyter NotebookMITupdated Oct 25, 2026
GitHub โ†—โ˜… 21.6Kโ‘‚ 3.1K
Sentiment Analysis๐Ÿฅ‰#3

PaddlePaddle/PaddleNLP

โ–ฒ +6 โ˜… this week

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

๐Ÿง  Natural Language Processingโ›๏ธ Information Extractionโ“ Question Answering
PythonApache-2.0updated May 23, 2026
GitHub โ†—โ˜… 13Kโ‘‚ 3K
Sentiment Analysis#4

QwenAudio/SenseVoice

โ–ฒ +48 โ˜… this week

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

๐ŸŽ™๏ธ Speech Recognition
CMITupdated Sep 30, 2026
GitHub โ†—โ˜… 9.7Kโ‘‚ 848
Sentiment Analysis#5

clips/pattern

โ–ฒ +1 โ˜… this week

Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.

๐Ÿง  Natural Language Processing
PythonBSD-3-Clauseupdated Aug 5, 2026
GitHub โ†—โ˜… 8.9Kโ‘‚ 1.5K
Sentiment Analysis#6

axa-group/nlp.js

โ–ฒ +5 โ˜… this week

An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more

๐Ÿง  Natural Language Processing๐Ÿท๏ธ Named Entity Recognition
JavaScriptMITupdated Jan 9, 2025
GitHub โ†—โ˜… 6.6Kโ‘‚ 633
Sentiment Analysis#7

udacity/deep-learning-v2-pytorch

โ–ฒ +1 โ˜… this week

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

Jupyter NotebookMITupdated Nov 4, 2026
GitHub โ†—โ˜… 5.5Kโ‘‚ 5.3K
Sentiment Analysis#8

bentrevett/pytorch-sentiment-analysis

Tutorials on getting started with PyTorch and TorchText for sentiment analysis.

๐Ÿง  Natural Language Processing๐Ÿงฌ Embeddings
Jupyter NotebookMITupdated Mar 27, 2024
GitHub โ†—โ˜… 4.6Kโ‘‚ 1.2K
Sentiment Analysis#9

CLUEbenchmark/CLUEDatasetSearch

ๆœ็ดขๆ‰€ๆœ‰ไธญๆ–‡NLPๆ•ฐๆฎ้›†๏ผŒ้™„ๅธธ็”จ่‹ฑๆ–‡NLPๆ•ฐๆฎ้›†

๐Ÿท๏ธ Named Entity Recognition๐Ÿ“ Text Summarization๐Ÿ—‚๏ธ Text Classification๐ŸŒ Machine Translation๐Ÿ” Search & Retrieval๐Ÿง  Natural Language Processing
Pythonno licenseupdated Nov 21, 2022
GitHub โ†—โ˜… 4.5Kโ‘‚ 621
Sentiment Analysis#10

JohnSnowLabs/spark-nlp๐Ÿ”ฅ active

โ–ฒ +3 โ˜… this week

State of the Art Natural Language Processing

๐Ÿง  Natural Language Processing๐Ÿท๏ธ Named Entity Recognition๐Ÿ—‚๏ธ Text Classificationโ“ Question Answering๐ŸŒ Machine Translationโœ‚๏ธ Tokenization & Preprocessing
ScalaApache-2.0updated Nov 12, 2026
GitHub โ†—โ˜… 4.2Kโ‘‚ 743
Sentiment Analysis#11

vladmandic/human

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

HTMLMITupdated Dec 13, 2025
GitHub โ†—โ˜… 3.4Kโ‘‚ 458
Sentiment Analysis#12

guillaume-be/rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

๐Ÿง  Natural Language Processing๐Ÿท๏ธ Named Entity Recognitionโ“ Question Answering
RustApache-2.0updated Jan 13, 2026
GitHub โ†—โ˜… 3.1Kโ‘‚ 247
Sentiment Analysis#13

thisandagain/sentiment

AFINN-based sentiment analysis for Node.js.

๐Ÿง  Natural Language Processing
JavaScriptMITupdated May 18, 2020
GitHub โ†—โ˜… 2.7Kโ‘‚ 309
Sentiment Analysis#14

blmoistawinde/HarvestText

ๆ–‡ๆœฌๆŒ–ๆŽ˜ๅ’Œ้ข„ๅค„็†ๅทฅๅ…ท๏ผˆๆ–‡ๆœฌๆธ…ๆด—ใ€ๆ–ฐ่ฏๅ‘็Žฐใ€ๆƒ…ๆ„Ÿๅˆ†ๆžใ€ๅฎžไฝ“่ฏ†ๅˆซ้“พๆŽฅใ€ๅ…ณ้”ฎ่ฏๆŠฝๅ–ใ€็Ÿฅ่ฏ†ๆŠฝๅ–ใ€ๅฅๆณ•ๅˆ†ๆž็ญ‰๏ผ‰๏ผŒๆ— ็›‘็ฃๆˆ–ๅผฑ็›‘็ฃๆ–นๆณ•

๐Ÿท๏ธ Named Entity Recognitionโ›๏ธ Information Extraction๐Ÿ“ Text Summarization๐Ÿง  Natural Language Processing
PythonMITupdated May 13, 2024
GitHub โ†—โ˜… 2.6Kโ‘‚ 341
Sentiment Analysis#15

shirosaidev/stocksight

โ–ฒ +3 โ˜… this week

Stock market analyzer and predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis

๐Ÿง  Natural Language Processing
PythonApache-2.0updated Dec 5, 2023
GitHub โ†—โ˜… 2.6Kโ‘‚ 494
Sentiment Analysis#16

curiousily/Getting-Things-Done-with-Pytorch

โ–ฒ +2 โ˜… this week

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BER

๐Ÿง  Natural Language Processing
Jupyter NotebookApache-2.0updated Jun 30, 2024
GitHub โ†—โ˜… 2.5Kโ‘‚ 638
Sentiment Analysis#17

achillesrasquinha/bulbea

:boar: :bear: Deep Learning based Python Library for Stock Market Prediction and Modelling

PythonOtherupdated Jan 17, 2021
GitHub โ†—โ˜… 2.3Kโ‘‚ 486
Sentiment Analysis#18

baidu/Senta

Baidu's open-source Sentiment Analysis System.

๐Ÿง  Natural Language Processing
PythonApache-2.0updated Aug 20, 2024
GitHub โ†—โ˜… 2Kโ‘‚ 360
Sentiment Analysis#19

corollari/linusrants

โ–ฒ +3 โ˜… this week

Dataset of Linus Torvalds' rants classified by negativity using sentiment analysis

Pythonno licenseupdated Sep 15, 2020
GitHub โ†—โ˜… 1.9Kโ‘‚ 36
Sentiment Analysis#20

jsksxs360/How-to-use-Transformers

Transformers ๅบ“ๅฟซ้€Ÿๅ…ฅ้—จๆ•™็จ‹

๐Ÿง  Natural Language Processing๐Ÿท๏ธ Named Entity Recognition๐Ÿ“ Text Summarization
PythonApache-2.0updated Feb 24, 2026
GitHub โ†—โ˜… 1.9Kโ‘‚ 226
Sentiment Analysis#21

dipanjanS/text-analytics-with-python

Learn how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python! This repository contains code and datasets used in my book, "Text Analytics with Python" published by Apress/Springer.

๐Ÿง  Natural Language Processing๐Ÿ“ Text Summarization๐Ÿ—‚๏ธ Text Classification๐Ÿ’Ž Text Mining
Jupyter NotebookApache-2.0updated Dec 24, 2020
GitHub โ†—โ˜… 1.7Kโ‘‚ 842
Sentiment Analysis#23

bfelbo/DeepMoji

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

๐Ÿง  Natural Language Processing๐Ÿ—‚๏ธ Text Classification
PythonMITupdated Aug 2, 2024
GitHub โ†—โ˜… 1.6Kโ‘‚ 305
Sentiment Analysis#24

declare-lab/conv-emotion

This repo contains implementation of different architectures for emotion recognition in conversations.

๐Ÿง  Natural Language Processing
PythonMITupdated Mar 10, 2024
GitHub โ†—โ˜… 1.5Kโ‘‚ 341
Sentiment Analysis#25

DemonDamon/FinnewsHunter๐Ÿ”ฅ active

โ–ฒ +1 โ˜… this week

FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.

PythonApache-2.0updated Nov 10, 2026
GitHub โ†—โ˜… 1.5Kโ‘‚ 344
Sentiment Analysis#26

obsei/obsei๐Ÿ”ฅ active

โ–ฒ +5 โ˜… this week

Open source, privacy-first Voice of Customer analytics. A self-hosted alternative to Enterpret and Unwrap that strips PII from feedback before any LLM sees it.

๐Ÿซง Topic Modeling๐Ÿง  Natural Language Processing
PythonApache-2.0updated Nov 11, 2026
GitHub โ†—โ˜… 1.5Kโ‘‚ 181
Sentiment Analysis#27

winkjs/wink-nlp

Developer friendly Natural Language Processing โœจ

๐Ÿง  Natural Language Processing๐Ÿท๏ธ Named Entity Recognition
JavaScriptMITupdated May 27, 2026
GitHub โ†—โ˜… 1.4Kโ‘‚ 65
Sentiment Analysis#28

lyeoni/nlp-tutorial

A list of NLP(Natural Language Processing) tutorials

๐Ÿง  Natural Language Processing๐Ÿ—‚๏ธ Text Classification๐ŸŒ Machine Translation
Jupyter NotebookMITupdated Apr 1, 2020
GitHub โ†—โ˜… 1.4Kโ‘‚ 261
Sentiment Analysis#30

SeanLee97/xmnlp

xmnlp๏ผšๆไพ›ไธญๆ–‡ๅˆ†่ฏ, ่ฏๆ€งๆ ‡ๆณจ, ๅ‘ฝๅไฝ“่ฏ†ๅˆซ๏ผŒๆƒ…ๆ„Ÿๅˆ†ๆž๏ผŒๆ–‡ๆœฌ็บ ้”™๏ผŒๆ–‡ๆœฌ่ฝฌๆ‹ผ้Ÿณ๏ผŒๆ–‡ๆœฌๆ‘˜่ฆ๏ผŒๅๆ—้ƒจ้ฆ–๏ผŒๅฅๅญ่กจๅพๅŠๆ–‡ๆœฌ็›ธไผผๅบฆ่ฎก็ฎ—็ญ‰ๅŠŸ่ƒฝ

๐Ÿท๏ธ Named Entity Recognition๐Ÿงฌ Embeddingsโœ‚๏ธ Tokenization & Preprocessing๐Ÿง  Natural Language Processing
PythonApache-2.0updated Nov 12, 2022
GitHub โ†—โ˜… 1.3Kโ‘‚ 181

๐Ÿ“„ New research on Sentiment Analysis

๐Ÿ“„ arXiv:2611.13744 ยท cs.CL2d ago

Do Language Models Feel the Sentiment? Investigating Emotion Vectors

Ali Hassan Khan, Saad Bin Ather, Muhammad Saif +2

๐Ÿ’ฌ 16 pages, 3 figures, 11 tables. Accepted at ExplAI-2026: 2nd Workshop on Advanced AI in Explainability and Ethics for the Sustainable Development Goals

Emotion vectors are directions in a language model's internal representations that are associated with emotional concepts. Prior work shows that these vectors can influence model behavior, but their role in sentiment classification remains unclear. This study investigates emotion directions in Qwen2.5-0.5B-Instruct and Qwen2.5-3B-Instruct. Eight directions extracted from GoEmotions are evaluated through sentiment probing, activation interventions, and supervised correction. Emotion-only probes achieve 88.66% and 90.70% accuracy on binary TweetEval. In exploratory matched-ablation experiments, raw emotion-space removal causes 2.39 and 1.10 percentage points more accuracy loss than matched isotropic random-subspace removal for 0.5B and 3B, respectively. All four TweetEval raw and denoised effects are significant after Holm adjustment across eight comparisons. An exploratory SST-2 extension shows smaller raw excess losses of 0.66 and 0.57 points, with no effects surviving Holm adjustment. Frozen sentiment-correction classifiers are also tested on 20,000 Amazon Polarity reviews. Emotion-based correction improves accuracy over uncorrected Qwen, but does not consistently outperform margin-only baselines. These results distinguish sentiment information available in model representations, the effects of changing those representations, and their practical value for classification. They do not establish a uniquely emotional mechanism.โ–ผ more
๐Ÿ’– Sentiment Analysis๐Ÿค– Language Models
๐Ÿ“„ arXiv:2611.13689 ยท eess.AS2d ago

Walrus Technical Report

Alkis Koudounas, Osamu Take, Hayato Futami +2

๐Ÿ’ฌ 30 pages, 3 figures, technical report

We present Walrus, a unified 8B speech-and-audio foundation model handling speech recognition (including code-switching and multi-talker speech), speech-to-text and speech-to-speech translation, text-to-speech, emotion recognition, audio captioning, and general audio understanding. Our main contribution is not a new architecture but a data-centric training recipe; we use a standard decoder-only backbone initialized from Gemma 4, so that gains can be traced to the data. For speech generation, Walrus predicts low-bitrate discrete speech tokens, and a lightweight token-to-waveform decoder converts them into high-fidelity audio. The recipe is a three-stage data curriculum that moves from broad multilingual data to multi-talker, code-switching, and domain-specific data. At each stage, task-aware and dataset-aware weighting balances tasks with very different token budgets and protects core skills from forgetting. Trained on over 600M samples covering more than 20 tasks and 100 languages, Walrus leads on most multilingual, multi-talker, and code-switching ASR, speech translation, and audio understanding benchmarks, outperforming both open speech language models of comparable size and dedicated task-specific models. On most benchmarks, it even matches or surpasses the $4\times$ larger Qwen3-Omni's performance. Results suggest that data engineering is a primary driver of quality in multi-task speech and audio modeling.โ–ผ more
๐Ÿ’– Sentiment Analysis๐ŸŒ Machine Translation๐ŸŽ™๏ธ Speech Recognition๐Ÿค– Language Models
๐Ÿ“„ arXiv:2611.12592 ยท cs.CL3d ago

Fairness in Explainable AI Narratives: Decomposing Social Disparities in LLM-Generated Explanations

Wannes Van den Bulck, Sofie Goethals, David Martens

๐Ÿ’ฌ 25 pages, 8 figures, 9 tables. Code, prompts, narratives and extractions available at https://github.com/WannesVandenBulck/fairxain

Large language models (LLMs) are increasingly used to translate technical explainable AI (XAI) artefacts such as SHAP into explanatory narratives (XAINs) for lay users. In high-risk domains, these explanations are often the main resource through which individuals can understand and contest adverse decisions. Yet LLMs are known to reproduce social bias, even from proxy variables alone, and fairness in XAINs remains unstudied. Because XAINs are bound to a ground-truth artefact, fairness concerns not only what a narrative says and how, but also whether it is equally faithful across social groups. We introduce fairness in XAINs as a new field of research and propose a framework that generates narratives under three conditions (protected attribute disclosed, withheld, or counterfactually swapped), allowing five comparisons that pinpoint the cause of disparities. We apply it to adversely classified instances from four datasets in credit scoring, education and employment, generating narratives with five LLMs, and evaluate faithfulness, feature coverage and sentiment. We find significant disparities across all datasets, metric families and models, arising in two ways. Faithfulness disparities result from feature values: LLMs make plausible but false statements, triggered by values that are unequally distributed across social groups. Feature coverage and sentiment disparities stem from the protected attribute itself: once it is disclosed, LLMs give less explanation to, or frame more negatively the narratives of, groups that have historically been discriminated against or are stereotypically associated with worse outcomes. A more faithful model removes the faithfulness disparities, and withholding protected attributes mostly removes the others, but neither suffices on its own. Fairness in XAINs should therefore be audited separately from the predictive model and its XAI artefact.โ–ผ more
๐Ÿ’– Sentiment Analysis๐Ÿค– Language Models
๐Ÿ“„ arXiv:2611.11987 ยท cs.CL3d ago

When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition

Youngseok Kim, Minjae Kim, Eunsoo Lee +1

๐Ÿ’ฌ 40 pages, 3 figures, 24 tables. Full version with appendices of a paper accepted at AICompS 2026 (Springer CCIS). Code and data: https://doi.org/10.5281/zenodo.23970406

Multimodal Emotion Recognition in Conversation (MERC) combines lexical, acoustic, visual and conversational cues, but accepting audio and video does not establish their effective or robust use. We audit off-the-shelf Omni models while holding the target transcript and prior textual context fixed and adding, removing or replacing target audio and video. In the primary evaluation of Qwen2.5-Omni-7B, Baichuan-Omni-1.5 and MiniCPM-o 2.6 on MELD and the full five-session six-class IEMOCAP set, T+A improves Accuracy in all six model-dataset pairs, with four gains significant after false discovery rate (FDR) correction. Across three source mappings, unrelated A/V (RandA/V) lowers Accuracy relative to Full in all 18 comparisons; all 18 remain significant under dialogue-cluster inference and BH-FDR correction, both on common-valid pairs and when invalid/OOM outcomes are treated as incorrect. Comparisons with modality-omission baselines further distinguish replacement penalties from mismatch-specific harm. A Qwen/MELD case study finds significantly greater gold-vs-best-candidate margin recovery in Late than Early or Middle under decision-query audio knockout, relative to an edge-count-matched Video-Sham control, using Holm-corrected tests. These results distinguish genuine-modality benefit from sensitivity and vulnerability to misleading input.โ–ผ more
๐Ÿ’– Sentiment Analysis๐ŸŽ™๏ธ Speech Recognition