---
id: wiki-2026-0508-sentiment-analysis-models
title: Sentiment Analysis Models
category: 10_Wiki/Topics
status: duplicate
canonical_id: sentiment-analysis
duplicate_of: "[[Sentiment-Analysis]]"
aliases: []
source_trust_level: A
confidence_score: 0.9
verification_status: redirected
tags: [duplicate, nlp, sentiment]
last_reinforced: 2026-05-10
github_commit: pending
---

# Sentiment Analysis Models

> **이 문서는 [[Sentiment-Analysis]] 의 중복본입니다.** Canonical 문서로 redirect.

## 핵심 요약 (model-specific aspects)
- Lexicon (VADER, TextBlob) — 매 zero-shot, weak.
- Classical ML (NB, SVM + TF-IDF) — 매 baseline.
- Fine-tuned BERT/RoBERTa (cardiffnlp/twitter-roberta) — 매 production default 2020-2024.
- LLM zero/few-shot (Claude, GPT-4o, Llama 3) — 매 2026 default for nuance, aspect-based.

## 🔗 Graph
- 부모: [[Sentiment-Analysis]] (canonical)

## 🕓 변경 이력
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | 중복 처리 — canonical 문서로 redirect |