Sentimental analysis of twitter tweets using machine learning algorithms
Arava Choudhary, Aayush Kawadia, Neetu Joshi · IET conference proceedings. · 2025
Machine Learning (ML) has become transformative across various industries, allowing computers to decide without explicit programming by using data to learn. This paper examines the theoretical and practical aspects of machine learning, with a focus on significant supervised learning techniques like Decision Tree, Support Vector Machines, Linear Regression, Logistic Regression, K-Nearest Neighbors and ensemble approaches like Bagging and Boosting. In addition, it is demonstrated how the exploratory data analysis (EDA) stage is crucial for the comprehension and preparation of data for the machine learning models. Even though the main emphasis is on supervised learning, the paper includes some notes on unsupervised learning in order to emphasize the most general features of the scope of ML in working with unstructured data. Using these methods, we are able to enhance the accuracy, the speed, and the scope of forecasting models. The paper describes empirical cases and evaluation in order to free these techniques from the encumbrance of the theoretical domain and to demonstrate their applicability to practical tasks.