NLP-CIC at SemEval-2020 Task 9: Analysing sentiment in code-switching language using a simple deep-learning classifier

TL;DR

This paper presents a straightforward deep-learning approach using CNNs to analyze sentiment in code-switched Spanish-English tweets, achieving competitive results and highlighting key challenges in this complex task.

Contribution

It introduces a simple CNN-based method for sentiment analysis in code-switching language, demonstrating effectiveness and providing insights through error analysis.

Findings

Achieved an F1-score of 0.71 on the test set.

Identified key difficulties in classifying sentiment in code-switched text.

Analyzed model capabilities and error patterns.

Abstract

Code-switching is a phenomenon in which two or more languages are used in the same message. Nowadays, it is quite common to find messages with languages mixed in social media. This phenomenon presents a challenge for sentiment analysis. In this paper, we use a standard convolutional neural network model to predict the sentiment of tweets in a blend of Spanish and English languages. Our simple approach achieved a F1-score of 0.71 on test set on the competition. We analyze our best model capabilities and perform error analysis to expose important difficulties for classifying sentiment in a code-switching setting.