Fine-tuning VADER Classifier with Domain-specific Lexicons

Petr Korab
Towards AI
Published in
6 min readMay 13, 2023

--

Extending the core VADER sentiment classifier’s lexicon with two financial lexicons improves sentiment classification accuracy from 58 % to 69 % on a classic financial dataset

Photo by Anna Nekrashevich on Pexels

Introduction

VADER (Valence Aware Dictionary and sEntiment Reasoner) classifier is a mainstream model for sentiment analysis frequently used in companies and…

--

--

Post-doc at Zeppelin University / Python engineer / text mining / data Viz