C1 at SemEval-2020 Task 9: SentiMix: Sentiment Analysis for Code-Mixed Social Media Text using Feature Engineering

In today's interconnected and multilingual world, code-mixing of languages on\nsocial media is a common occurrence. While many Natural Language Processing\n(NLP) tasks like sentiment analysis are mature and well designed for\nmonolingual text, techniques to apply these tasks to code-mixed text still\nwarrant exploration. This paper describes our feature engineering approach to\nsentiment analysis in code-mixed social media text for SemEval-2020 Task 9:\nSentiMix. We tackle this problem by leveraging a set of hand-engineered\nlexical, sentiment, and metadata features to design a classifier that can\ndisambiguate between "positive", "negative" and "neutral" sentiment. With this\nmodel, we are able to obtain a weighted F1 score of 0.65 for the "Hinglish"\ntask and 0.63 for the "Spanglish" tasks\n