
Improving the sentiment analysis of sarcastic tweets using machine learning and natural language processing
With the developing technology, the number of comments made on the internet is increasing day by day. It is difficult to make a manual sentiment analysis on these comments. Therefore, new algorithms should be developed to automatically perform sentiment analysis on these texts for companies. In this study, a sentiment analysis model using machine learning and NLP (Natural Language Processing) algorithms are compared. While developing this model, CNN (Convolutional Neural Network) methods and machine learning algorithms were used together. As a naïve method of sentiment analysis, the root of each word in a sentence takes a score from a dictionary and the final polarity score of the relevant sentence is calculated by using additive score-based models. Machine learning models and Natural Language Processing models were trained to perform accurate sentiment annotations by using features based on polarity scores of texts. This analysis was conducted on 10,000 tweets using publicly available data from Kaggle. The results showed that NLP outperforms machine learning algorithms and gives better accuracy.
Files
Metadata
Work Title | Improving the sentiment analysis of sarcastic tweets using machine learning and natural language processing |
---|---|
Access | |
Creators |
|
Keyword |
|
License | In Copyright (Rights Reserved) |
Work Type | Masters Culminating Experience |
Acknowledgments |
|
Publication Date | May 2021 |
Language |
|
DOI | doi:10.26207/3d32-2w26 |
Geographic Area |
|
Deposited | May 19, 2021 |