Assessing Sentiment Strength in Words Prior Polarities

TL;DR

This paper evaluates methods for deriving a word's overall sentiment polarity from its multiple senses, comparing 14 formulas to determine which best aligns with human judgments using regression and classification.

Contribution

It systematically compares 14 prior polarity computation formulas to identify the most accurate method for sentiment analysis.

Findings

Identifies the most effective formula for estimating prior polarity.

Provides a comprehensive comparison of existing polarity aggregation methods.

Enhances sentiment analysis accuracy by selecting optimal polarity computation.

Abstract

Many approaches to sentiment analysis rely on lexica where words are tagged with their prior polarity - i.e. if a word out of context evokes something positive or something negative. In particular, broad-coverage resources like SentiWordNet provide polarities for (almost) every word. Since words can have multiple senses, we address the problem of how to compute the prior polarity of a word starting from the polarity of each sense and returning its polarity strength as an index between -1 and 1. We compare 14 such formulae that appear in the literature, and assess which one best approximates the human judgement of prior polarities, with both regression and classification models.