Modeling Word Emotion in Historical Language: Quantity Beats Supposed Stability in Seed Word Selection

TL;DR

This paper develops methods to estimate historical word emotions using Valence-Arousal-Dominance, creating a new gold standard and showing that quantity of seed words is more effective than stability assumptions.

Contribution

It adapts emotion induction algorithms to the VAD scheme and introduces the first gold standard for historical English and German word emotions.

Findings

Seed word stability assumptions are harmful.

Quantity of seed words improves emotion estimation.

First gold standard for historical word emotions created.

Abstract

To understand historical texts, we must be aware that language -- including the emotional connotation attached to words -- changes over time. In this paper, we aim at estimating the emotion which is associated with a given word in former language stages of English and German. Emotion is represented following the popular Valence-Arousal-Dominance (VAD) annotation scheme. While being more expressive than polarity alone, existing word emotion induction methods are typically not suited for addressing it. To overcome this limitation, we present adaptations of two popular algorithms to VAD. To measure their effectiveness in diachronic settings, we present the first gold standard for historical word emotions, which was created by scholars with proficiency in the respective language stages and covers both English and German. In contrast to claims in previous work, our findings indicate that hand-selecting small sets of seed words with supposedly stable emotional meaning is actually harmful rather than helpful.