In the age of social media, Twitter has emerged as one of the largest platforms for expressing personal opinions and emotions. The vast volume of real-time data shared by users offers unique opportunities for analyzing public sentiment on various topics, including politics, entertainment, and social issues. However, extracting meaningful insights from such unstructured data presents significant challenges. Traditional sentiment analysis methods often struggle with the nuances of language, such as sarcasm, irony, and the context-dependent meaning of words. Thus, there is a need for more advanced techniques to improve the accuracy and efficiency of sentiment classification. This study proposes a novel approach to sentiment analysis of tweets using deep learning, specifically by leveraging the ResNet architecture. ResNet, a powerful deep convolutional neural network, has shown remarkable performance in image processing tasks and is adapted here for text-based sentiment analysis. The method involves preprocessing the tweet data, embedding it into word vectors, and passing it through a ResNet-based model. The model utilizes residual connections to overcome the vanishing gradient problem, enabling it to learn deeper representations of the tweet text and capture complex semantic features. The outcomes of this research demonstrate that the ResNet model outperforms traditional machine learning models, such as support vector machines (SVM) and logistic regression, in terms of both accuracy and efficiency. The proposed method achieves high classification performance, correctly categorizing tweets into positive, negative, or neutral sentiments. These results highlight the potential of deep learning techniques, particularly ResNet, in effectively analyzing social media content for sentiment detection, offering valuable insights for businesses, researchers, and decision-makers.
M. Patel, R.V. Vikram
Rajarambapu Institute of Technology, India
Sentiment Analysis, Twitter, Deep Learning, ResNet, Text Classification
| January | February | March | April | May | June | July | August | September | October | November | December |
| 5 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Data Science and Machine Learning
( Volume: 6 , Issue: 1 , Pages: 729 - 734 )
Date of Publication :
December 2024
Page Views :
16
Full Text Views :
5
|