Sentiment-Analysis-and-Offensive-Language-Identification

Abstract

The main source of our project describes our two tasks that are: Sentiment Analysisand Offensive Language Identification on Dravidian Languages (Tamil and Malayalam).These tasks are a popular task for some years. The dataset we used will contain fullof code mixed text. Extracting Sentiments and finding Offensive from the sentenceis a challenging task. Our first aim of this project is to clear noisy texts and removingunnecessary contents. Then we had created baseline models by training the traditionalMachine Learning (ML) models, such as Support Vector Machine (SVM), Naïve BayesClassifier, Logistic Regression, and Random Forest with feature vectors are extractedby using the TF-IDF method. Then we created Neural Network models such as Multi-layer Perceptron (MLP) and Long Short-Term Memory (LSTM). Here, we had extractedfeatures by using Word2Vec one-hot Method. The above methods are performed thesame for Sentiment Analysis and Offensive Language Identification. As we will see,the Traditional machine learning algorithms are much better in performance than theNeural Network approachs with the F1 scores.