SentiStrength home

SentiStrengthSentiStrength Citation Context

This page has SentiStrength variants for detecting sentiment in texts containing citations.

SentiStrength estimates the strength of positive and negative sentiment in short texts, even for informal language. It has human-level accuracy for short social web texts in English, except political texts. SentiStrength reports two sentiment strengths:

-1 (not negative) to -5 (extremely negative)

1 (not positive) to 5 (extremely positive)

This is designed for detecting sentiment about the cited reference within a citing sentence. Versions of the algorithm will be introduced for different academic fields.

For Natural Language Processing (NLP) and data mining.


SentiStrength was produced as part of the CyberEmotions project, supported by EU FP7.