cjhutto/vaderSentiment

Incorrect results for sentences containing negations

Open

#71 opened on Jan 13, 2019

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (4,146 stars) (975 forks)batch import
help wanted

Description

Hi

First of all, great work!

I've noticed some negations are analysed incorrectly. For instance,

Not the worst show I've seen-------- {'neg': 0.0, 'neu': 0.603, 'pos': 0.397, 'compound': 0.5096} Not the worst ever but definitely worst this year------ {'neg': 0.0, 'neu': 0.372, 'pos': 0.628, 'compound': 0.879}

The compound scores are incorrectly positive as these two sentences are neural at best.

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Python programmingSentiment analysis basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65
Research direction
Investigate the vaderSentiment library's handling of negation in the lexicon and score computation. Look at the source code (e.g., vaderSentiment.py) to understand how negations like 'not' are processed. Modify the rule for negations to correctly flip the sentiment polarity for phrases like 'not the worst'. Test with given examples and ensure compound score is negative.