Αναγνώριση τάσης σε ροές δεδομένων κειμένου
Sentiment analysis in text data streams
View/
Keywords
Sentiment analysis ; Twitter ; Marching learning ; Neural networks ; RNN ; CNN ; Naive Bayes ; Random forest ; Gradient boosting ; SVM ; GhatGtpAbstract
This thesis aims to evaluate the accuracy of machine learning and neural network models in sentiment analysis of Twitter data. With the increasing importance of social media data for business and society, sentiment analysis has become a crucial tool to understand public opinion and make informed decisions. The study will focus on sentiment analysis of English tweets and compare the performance of four models Naive Bayes, Decision Tree, Random Forest, SVM, Gradiaent Boost- and two neural networks - RNN, CNN - based on evaluation metrics such as accuracy, precision, recall, and F1 score. The method involves data collection and pre-processing, feature extraction, and the implementation of machine learning and neural network models. The evaluation process will compare the performance of the models and visualize the results. The study aims to contribute to the literature on sentiment analysis in Twitter using machine learning and neural networks and supply insights into the performance of various models in sentiment analysis of Twitter data. The results of the study could be useful for businesses, government agencies, and other organizations in understanding public opinion related to COVID-19 and making informed decisions based on the sentiment analysis.
Postgraduate Studies Programme
Εφαρμοσμένη ΣτατιστικήDepartment
Σχολή Χρηματοοικονομικής και Στατιστικής. Τμήμα Στατιστικής και Ασφαλιστικής ΕπιστήμηςNumber of pages
118Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα