A Deep Learning Approach for Twitter Sentiment Analysis using ULM-SVM

Through Twitter sentiment Analysis, users can easily determine the quality of their products and services. These tools are very useful in identifying and monitoring the various factors that affect the quality of these services and products. The classification accuracy of these tools is dependent on the quality of the input features and the techniques used. Unfortunately, the time constraints associated with implementing machine learning techniques can prevent many organizations from achieving their goals. Deep learning techniques are used in various applications, such as sentiment analysis, to extract information from large amounts of data. The goal of this study is to develop a new method for analyzing sentiment that uses deep learning techniques. This method combines the features of a ULM-SVM. The proposed method employs deep learning techniques to analyze Twitter sentiment, which seeks to identify the users' sentiments toward particular products based on their posts. The evaluation of the model across three datasets revealed its exceptional performance, achieving an accuracy of 98.7% in detecting sentiment on the dataset.