awesome-sentiment-analysis
github.com/laugustyniak/awesome-sentiment-analysis ↗Repository with all what is necessary for sentiment analysis and related areas
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me parameter-efficient fine-tuning (peft) resources from awesome-sentiment-analysis"
Installation instructions →What's inside
LLM Techniques for Sentiment Analysis
- 2025 Guide to Fine-Tuning: LoRA, QLoRA & Transfer LearningParameter-Efficient Fine-Tuning (PEFT)
- Comprehensive Survey of LLM Alignment: RLHF, RLAIF, PPO, DPO and MoreInstruction Tuning & Alignment
- Comprehensive Taxonomy of Prompt Engineering TechniquesPrompt Engineering
- Keras: LoRA and QLoRA fine-tuning of GemmaParameter-Efficient Fine-Tuning (PEFT)
- LangChainRetrieval-Augmented Generation (RAG)
- LangGraphRetrieval-Augmented Generation (RAG)
LLM Reliability & Safety in Sentiment Analysis
- [2026 tasks]International Workshops
Papers
- A BERT–LSTM–Attention Framework for Robust Multi-Class Sentiment Analysis on Twitter DataTransformer Models and RoBERTa (2023-2025)
Hybrid architecture combining BERT with BiLSTM and attention mechanisms for Twitter sentiment (2024)
- Advancing Sentiment Analysis: Evaluating RoBERTa against Traditional and Deep Learning ModelsTransformer Models and RoBERTa (2023-2025)
Comprehensive comparison showing RoBERTa achieving 96.30% accuracy and F1-scores of 98.11% on specific sentiment benchmarks (see paper for datasets and experimental setup) (2024)
- Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGRAG & Retrieval Methods (2024-2026)
- A multimodal approach to cross-lingual sentiment analysis with ensemble of transformer and LLMMultilingual and Cross-lingual Sentiment Analysis (2024-2026)
Ensemble method combining transformers and LLMs for cross-lingual sentiment (2024)
- Analyzing LLaMA3 Performance on Classification Using LoRA and QLoRA TechniquesParameter-Efficient Fine-Tuning (2025-2026)
- Analyzing student mental health with RoBERTa-Large: a sentiment analysis and data analytics approachDomain-Specific Applications (2024-2026)
Healthcare application for mental health monitoring (2025)
Resources
- AFINNLexicons
AFINN is a list of English words rated for valence with an integer between minus five (negative) and plus five (positive). The words have been manually labeled by Finn Årup Nielsen in 2009-2011.
- ALBERTPretrained Language Models
Parameter-efficient version of BERT with reduced memory consumption (Google, 2019)
- Amazon Product DatasetDatasets
This dataset contains product reviews and metadata from Amazon, including 142.8 million reviews spanning May 1996 - July 2014. This dataset includes reviews (ratings, text, helpfulness votes), product metadata (descriptions, category information, price, brand, and image features), and links (also viewed/also bought graphs). The updated version of dataset - update as for 2018 is availalbe here
- BERT-base, BERT-largePretrained Language Models
Original TensorFlow implementation (Google, 2018)
- BloombergGPTPretrained Language Models
50B parameter LLM for financial NLP including sentiment analysis
- Claude 4.5Pretrained Language Models
Advanced large language model widely used for sentiment and emotion analysis tasks, with strong performance on contemporary benchmarks
Libraries
- AFINN-based sentiment analysis for Node.jsTraditional Libraries
Sentiment is a Node.js module that uses the AFINN-165 wordlist and Emoji Sentiment Ranking to perform sentiment analysis on arbitrary blocks of input text.
- Aspect Based Sentiment AnalysisAspect-based Sentiment Analysis
System that participated in Semeval 2014 task 4: Aspect Based Sentiment Analysis.
- Aspect Based Sentiment Analysis using End-to-End Memory NetworksAspect-based Sentiment Analysis
TensorFlow implementation of
- ASUM JavaTraditional Libraries
Aspect and Sentiment Unification Model for Online Review Analysis.
- C++, MITIETraditional Libraries
MIT Information Extraction.
- Dragon Sentiment Classifier C#Traditional Libraries
Dragon Sentiment API is a C# implementation of the Naive Bayes Sentiment Classifier to analyze the sentiment of a text corpus.
API
Related Studies
- Benchmarking Multimodal Sentiment Analysis
multimodal sentiment analysis and emotion detection (text, audio and video).
Tutorials
- Build a brand monitoring agent
Python tutorial that searches news and the web for brand mentions, scrapes the full content, and uses an LLM to classify each mention's sentiment (positive/neutral/negative) and urgency for a daily digest.
- GPT2 For Text Classification using Hugging Face Transformers
GPT model application for sentiment analysis task
- LingPipe Sentiment
This tutorial covers assigning sentiment to movie reviews using language models. There are many other approaches to sentiment. One we use fairly often is sentence based sentiment with a logistic regression classifier. Contact us if you need more information. For movie reviews we focus on two types of classification problem: Subjective (opinion) vs. Objective (fact) sentences Positive (favorable) vs. Negative (unfavorable) movie reviews
Showing a sample of 211 resources. View the full list on GitHub →