Multilingual Topic Classification in X: Dataset and Analysis

TL;DR

This paper introduces X-Topic, a multilingual dataset for tweet classification across four languages, and analyzes the performance of various language models in understanding diverse social media content.

Contribution

The paper presents a new multilingual dataset, X-Topic, and provides a comprehensive analysis of language model capabilities in cross-linguistic social media classification.

Findings

X-Topic covers four languages with diverse social media topics

Current language models show varying effectiveness across languages

Multilingual models outperform monolingual models in cross-lingual tasks

Abstract

In the dynamic realm of social media, diverse topics are discussed daily, transcending linguistic boundaries. However, the complexities of understanding and categorising this content across various languages remain an important challenge with traditional techniques like topic modelling often struggling to accommodate this multilingual diversity. In this paper, we introduce X-Topic, a multilingual dataset featuring content in four distinct languages (English, Spanish, Japanese, and Greek), crafted for the purpose of tweet topic classification. Our dataset includes a wide range of topics, tailored for social media content, making it a valuable resource for scientists and professionals working on cross-linguistic analysis, the development of robust multilingual models, and computational scientists studying online dialogue. Finally, we leverage X-Topic to perform a comprehensive cross-linguistic and multilingual analysis, and compare the capabilities of current general- and domain-specific language models.