Exploring Sentiment Trends on Twitter: A Machine Learning Approach for Analyzing Public Opinion

Information Technology

With the exponential growth of web technology, the volume of data on the internet has reached unprecedented levels. The internet has evolved into a platform for online learning, idea exchange, and opinion sharing. Social networking sites such as Twitter, Facebook, and Google+ have gained immense popularity, enabling users to share views, engage in discussions, and post messages globally. This survey focuses on sentiment analysis of Twitter data, which is crucial for analyzing opinions expressed in tweets, known for their unstructured and heterogeneous nature. We provide an overview and comparative analysis of existing sentiment analysis techniques, including machine learning and lexicon-based approaches, along with evaluation metrics. We explore the use of machine learning algorithms such as Naive Bayes, Maximum Entropy, and Support Vector Machine for sentiment analysis of Twitter data streams. Additionally, we discuss the general challenges and applications of sentiment analysis on Twitter.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.