Adapting Deep Learning for Sentiment Classification of Code-Switched Informal Short Text
This addresses sentiment analysis for under-resourced informal and code-switched text, which is incremental as it adapts existing deep learning methods to a specific domain.
The paper tackled sentiment classification for code-switched informal short text by creating a labeled dataset (MultiSenti) and proposing a deep learning model that outperforms existing multilingual models, with character-based embeddings achieving equivalent performance more efficiently than word-based ones.
Nowadays, an abundance of short text is being generated that uses nonstandard writing styles influenced by regional languages. Such informal and code-switched content are under-resourced in terms of labeled datasets and language models even for popular tasks like sentiment classification. In this work, we (1) present a labeled dataset called MultiSenti for sentiment classification of code-switched informal short text, (2) explore the feasibility of adapting resources from a resource-rich language for an informal one, and (3) propose a deep learning-based model for sentiment classification of code-switched informal short text. We aim to achieve this without any lexical normalization, language translation, or code-switching indication. The performance of the proposed models is compared with three existing multilingual sentiment classification models. The results show that the proposed model performs better in general and adapting character-based embeddings yield equivalent performance while being computationally more efficient than training word-based domain-specific embeddings.