Emoji-Based Transfer Learning for Sentiment Tasks

TL;DR

This paper leverages emoji-encoded emotional information in a transfer learning framework to improve sentiment analysis and hate speech detection, especially in low-resource, multilingual contexts.

Contribution

It introduces a transfer learning method utilizing emoji-based source tasks to enhance sentiment analysis performance across languages and conditions.

Findings

Transfer is most effective with balanced, emoji-rich target data.

Monolingual source tasks outperform multilingual ones due to cultural emoji use.

Up to 0.280 F1 score improvement over baseline.

Abstract

Sentiment tasks such as hate speech detection and sentiment analysis, especially when performed on languages other than English, are often low-resource. In this study, we exploit the emotional information encoded in emojis to enhance the performance on a variety of sentiment tasks. This is done using a transfer learning approach, where the parameters learned by an emoji-based source task are transferred to a sentiment target task. We analyse the efficacy of the transfer under three conditions, i.e. i) the emoji content and ii) label distribution of the target task as well as iii) the difference between monolingually and multilingually learned source tasks. We find i.a. that the transfer is most beneficial if the target task is balanced with high emoji content. Monolingually learned source tasks have the benefit of taking into account the culturally specific use of emojis and gain up to F1 +0.280 over the baseline.