A Multilingual Corpus for Panic and Worry in Code-Mixed Tweets by VADER Sentiment Analysis

Abstract

The phenomenon of code-mixing in online discourse, on platforms such as X, offers an interesting setting to detect preliminary markers of anxiety within diverse linguistic expressions. The usage of more than one language within a single text or tweet necessitates the creation of a multilingual corpus to identify initial indicators of anxiety in code-mixed texts or tweets, contributing to a comprehensive understanding of mental health in the digital age. Existing research on code-mixed textual context primarily centres on code-mixed language of English with Spanish or Hindi, leaving a gap in our comprehension of other code-mixed languages, in particular; English with Malay or Indonesian language. Thus, our study focuses on anxiety-related linguistic expressions in Malay and Indonesian languages, such as ‘bimbang’, ‘bingung’, ‘panik’, ‘gelisah’, ‘cemas’, ‘takut’, ‘kacau’, ‘gemetar’, ‘gugup’, ‘teror’ and occasionally the usage of slangs such as ‘neves’, ‘gabra’, and ‘cape bgt’. In this paper, we introduce CORPUS4PANWO, an annotated sentiment-driven multilingual corpus for panic and worry detection in tweets. To experiment the corpus, we applied a corpus-based sentiment analysis utilizing VADER on diverse events, achieving accuracy of between 76.6% - 88.0% when used on tweets in negative circumstances. The corpus is a valuable resource for Southeast Asian linguistics, enabling exploration of emotional expression in diverse contexts.