An Empirical Analysis of the Role of Amplifiers, Downtoners, and Negations in Emotion Classification in Microblogs

TL;DR

This paper investigates how amplifiers, downtoners, and negations influence emotion classification in Twitter microblogs, proposing methods to improve accuracy and interpretability of emotion detection models.

Contribution

It introduces a scope detection method for modifiers, integrates it into emotion classification, and analyzes their semantic impact on emotion words in social media texts.

Findings

Amplifiers enhance the clarity of primary emotions.

Downtoners tend to weaken or alter emotion intensity.

Negations can shift the perceived emotion, e.g., 'not happy' closer to sadness.

Abstract

The effect of amplifiers, downtoners, and negations has been studied in general and particularly in the context of sentiment analysis. However, there is only limited work which aims at transferring the results and methods to discrete classes of emotions, e. g., joy, anger, fear, sadness, surprise, and disgust. For instance, it is not straight-forward to interpret which emotion the phrase "not happy" expresses. With this paper, we aim at obtaining a better understanding of such modifiers in the context of emotion-bearing words and their impact on document-level emotion classification, namely, microposts on Twitter. We select an appropriate scope detection method for modifiers of emotion words, incorporate it in a document-level emotion classification model as additional bag of words and show that this approach improves the performance of emotion classification. In addition, we build a term weighting approach based on the different modifiers into a lexical model for the analysis of the semantics of modifiers and their impact on emotion meaning. We show that amplifiers separate emotions expressed with an emotion- bearing word more clearly from other secondary connotations. Downtoners have the opposite effect. In addition, we discuss the meaning of negations of emotion-bearing words. For instance we show empirically that "not happy" is closer to sadness than to anger and that fear-expressing words in the scope of downtoners often express surprise.