A Deep Hybrid Learning Model for Classification of Code-Mixed Text

Social media consists of many tweets. These tweets consist of emotions like positive, negative. Many people use the bilingual sentences it means using two languages in a sentence. The main aim of the project is to develop a classification algorithm that can be used on social media data to classify it as positive or negative. Social media consists of code-mixed data which means more than one language has been used by the users. To classify the code-mixed data, we use classifiers to produce the emotions for the bilingual sentences. This project involves natural language processing, deep learning and machine learning algorithms. By mixing different classifying algorithms output we are going to increase the accuracy. The datasets are available for the linguistic languages. There are classifiers like CNN, LSTM and other machine learning classifiers like Adaptive boost are used to increase the accuracy and efficiency of the model.