Year: 2023
Type: conference-paper
Abstract: Social media platforms have become a part of our lives offering a wealth of real-time information and diverse perspectives, on different topics. Among these networks, Twitter stands out as a platform for expression and sharing emotions. With millions of users sharing their thoughts, feelings and experiences, Twitter has become a tool for understanding opinions on various subjects such as events, products and societal matters. In this abstract, I summarize a study on Twitter Sentiment Analysis (TSA) which aims to develop an automated system of extracting and evaluating sentiment from tweets. Using Natural Language Processing (NLP) techniques and machine learning algorithms the system analyzes amounts of data to identify and categorize attitudes as positive, negative or neutral. The methodology employed in this study requires access to a collection of tweets covering topics. To ensure accurate sentiment analysis results preprocessing techniques are applied to address issues like noise, misspellings and emojis. The sentiment analysis model is then. Refined using data. A comparative performance investigation revealed that the Support Vector Machine (SVM) classifier gives the best results, with the highest accuracy (94.73%) and F1 score (0.4994). The findings from this research demonstrate the effectiveness of the Twitter Sentiment Analysis system, in capturing and classifying sentiments expressed in tweets. Consequently, this research emphasizes the significance and potential of Twitter Sentiment Analysis, as an approach to examining prevailing sentiment. By utilizing Natural Language Processing (NLP) and other strategies the proposed system enhances sentiment analysis methods and their practical use in fields, through machine learning.
Institution: Indira Gandhi Delhi Technical University for Women
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391237255