Analysis of deep learning algorithms used for text classification- A review

Download Article
N Lavanya, Medishetti Vedavani, Hymavathi Sabbani, Rajesh Perugu

Abstract: To efficiently classify content, an assortment of different classification algorithms can be utilized. A classifier is developed using machine learning by identifying the features of categories from a set of training data gathered at established phases. Deep learning significantly enhances text classification, much as way they do so with lower-level engineering and processes. Natural language processing (NLP) activities that include sentiment analysis, question-answering, dialogue management, or word categorization based on semantics all depend upon text classification. The data is cleaned, missing values are imputed, and redundant columns are removed. Then, for classification, we use deep learning methods such as long short-term memory (LSTM), artificial neural network (ANN), and gated recurrent unit (GRU) as well as machine learning techniques such as logistic regression, random forest, and K-nearest neighbor’s (KNN). Results show that LSTM outperforms all other models and baseline studies, achieving 92% accuracy.

Natural language processing (NLP), artificial neural network (ANN)