IUST at SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text using Deep Neural Networks and Linear Baselines

Sentiment Analysis is a well-studied field of Natural Language Processing.\nHowever, the rapid growth of social media and noisy content within them poses\nsignificant challenges in addressing this problem with well-established methods\nand tools. One of these challenges is code-mixing, which means using different\nlanguages to convey thoughts in social media texts. Our group, with the name of\nIUST(username: TAHA), participated at the SemEval-2020 shared task 9 on\nSentiment Analysis for Code-Mixed Social Media Text, and we have attempted to\ndevelop a system to predict the sentiment of a given code-mixed tweet. We used\ndifferent preprocessing techniques and proposed to use different methods that\nvary from NBSVM to more complicated deep neural network models. Our best\nperforming method obtains an F1 score of 0.751 for the Spanish-English sub-task\nand 0.706 over the Hindi-English sub-task.\n