TY - JOUR
T1 - Anticipating impression using textual sentiment based on ensemble LRD model
AU - Karim, Abdul
AU - Mansab, Maria
AU - Shahroz, Mobeen
AU - Mushtaq, Muhammad Faheem
AU - Jeong, In cheol
N1 - Publisher Copyright:
© 2024
PY - 2025/3/5
Y1 - 2025/3/5
N2 - Twitter sentiment analysis is a natural language processing that analyzes the sentiments espoused in Twitter tweets, helping users understand others’ perspectives on specific issues or trends. The research aims to improve sentiment analysis applications across industries by optimizing machine learning models for accurate sentiment prediction in diverse textual data. The goal of this study is to make the development of strong ensemble learning models by utilizing a publicly available dataset, such as Twitter sentiment analysis through Kaggle. To carefully clean the data and remove any unnecessary information, preprocessing techniques are used. The data is divided into two sections to predict impressions: training data and testing data, and seven different machine learning methods are applied such as Naive Bayes Classifiers, Logistic Regression, Decision Trees, Support Vector Machines, Multilayer Perceptron, Gradient Boosting, three classifiers that were merged into one ensemble machine learning approach. To determine each words weight value within the text of a document, the TF-IDF technique is applied. The trained model is compared to testing data to determine how much variance exists between actual and expected values. The result is evaluated using evaluation parameters such as precision, recall, and F1 score. The maximum accuracy achieved by the ensemble LRD model is approximately 90.5 %. This study aims to enhance sentiment analysis in various industries and sentiment-based recommendation systems, by analyzing diverse texts and determining people's perspectives.
AB - Twitter sentiment analysis is a natural language processing that analyzes the sentiments espoused in Twitter tweets, helping users understand others’ perspectives on specific issues or trends. The research aims to improve sentiment analysis applications across industries by optimizing machine learning models for accurate sentiment prediction in diverse textual data. The goal of this study is to make the development of strong ensemble learning models by utilizing a publicly available dataset, such as Twitter sentiment analysis through Kaggle. To carefully clean the data and remove any unnecessary information, preprocessing techniques are used. The data is divided into two sections to predict impressions: training data and testing data, and seven different machine learning methods are applied such as Naive Bayes Classifiers, Logistic Regression, Decision Trees, Support Vector Machines, Multilayer Perceptron, Gradient Boosting, three classifiers that were merged into one ensemble machine learning approach. To determine each words weight value within the text of a document, the TF-IDF technique is applied. The trained model is compared to testing data to determine how much variance exists between actual and expected values. The result is evaluated using evaluation parameters such as precision, recall, and F1 score. The maximum accuracy achieved by the ensemble LRD model is approximately 90.5 %. This study aims to enhance sentiment analysis in various industries and sentiment-based recommendation systems, by analyzing diverse texts and determining people's perspectives.
KW - Ensemble learning
KW - Machine learning
KW - Sentiment analysis
KW - Social media
KW - Twitter
UR - http://www.scopus.com/inward/record.url?scp=85208915346&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2024.125717
DO - 10.1016/j.eswa.2024.125717
M3 - Review article
AN - SCOPUS:85208915346
SN - 0957-4174
VL - 263
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 125717
ER -