What question did this study set out to answer?

This research aims to introduce the WKWSCI Sentiment Lexicon and evaluate its effectiveness against five existing sentiment lexicons.

Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons

View Full Paper

Ask AI

Bookmark

This research aims to introduce the WKWSCI Sentiment Lexicon and evaluate its effectiveness against five existing sentiment lexicons.
Compared six sentiment lexicons using Amazon product review and news headlines datasets.
Evaluated sentiment categorisation accuracy at both document and sentence levels.
Analyzed performance using weights for sentiment word categories and simple counting methods.
WKWSCI, MPQA, Hu & Liu and SO-CAL lexicons achieved 75%-77% accuracy on product reviews.
Hu & Liu lexicon performed best without a training corpus on product review sentiment categorisation.
WKWSCI achieved 69% accuracy on news headlines with a Pearson correlation of 0.57 to human-assigned values.

No takes yet. Share an insight, caveat, or question.

Comparative evaluation of sentiment lexicons shows varying effectiveness in sentiment categorisation across document types.

Khoo et al. (2017) studied this question.

View Full Paper

Ask AI

Bookmark