Contextual effects of sentiment deployment in human and machine translation

TL;DR

This paper examines how sentiment shifts during translation and its impact on automated sentiment analysis, highlighting differences between human and machine translation in preserving semantic content.

Contribution

It reveals that machine translation reduces the semantic richness of texts more than human translation, affecting sentiment analysis accuracy.

Findings

Machine translation decreases the semantic field of texts.

Human translation better preserves sentiment and semantic content.

Implications for automated sentiment analysis accuracy.

Abstract

This paper illustrates how the overall sentiment of a text may be shifted in translation and the implications for automated sentiment analyses, particularly those that utilize machine translation and assess findings via semantic similarity metrics. While human and machine translation will produce more lemmas that fit the expected frequency of sentiment in the target language, only machine translation will also reduce the overall semantic field of the text, particularly in regard to words with epistemic content.