Sentiment Analysis and Comprehensive Evaluation of Supervised Machine Learning Models Using Twitter Data on Russia–Ukraine War

Abstract

The Russia–Ukrainian War refers to the ongoing hostilities between Russia and Ukraine. It was first focused on whether Crimea and the Donbass were formally recognised as being a part of Ukraine when Russia started it in February 2014. The conflict dramatically grew when Russia began its incursion of Ukraine on February 24, 2022, following a military build-up on the Russian–Ukrainian border that started in late 2021. Examining public perceptions of the crisis between Russia and Ukraine is the goal of this piece. These days, social media has taken on a significant role in communication, and as a result, opinions can be found on platforms like Facebook, Twitter, and Instagram. The study makes use of his 11,250 tweets about the war between Russia and Ukraine from his Twitter account. Techniques, including image processing, object identification, and natural language processing, have shown application, power, and potential for machine learning. The same applies to text analytics. For text analysis, sentiment analysis, and entity annotation, machine learning techniques are frequently employed. According to the applicability and efficacy of the machine learning model, natural language processing toolkit in python is utilised in to examine the textual polarity and subjectivity score of tweets. Moreover, because machine learning models have a high degree of classification accuracy, they have been widely utilised to categorise emotions. We have developed and test models using three feature extraction techniques: TF-IDF (term frequency-inverse document frequency), BoW (bag of words), and N -gram. Each model was assessed using a number of important performance indicators, including accuracy, precision, recall, and F 1 score. Results show that the extra trees classifier (ETC) model achieves a highest accuracy of 0.84 in combination with the Bow property which is a measure to evaluate the efficacy of a machine learning algorithm. Logistic regression (LR), decision tree (DT), support vector machine (SVM), XGB, Gaussian naive base (GNB), ADA, and K -nearest neighbours (KNN) comparison have also been made.

Hybrid Deep Learning Approach for Classification and Analysis of X Posts on Russia Ukraine War

“…The maximum level of text data as tweets are adorned with such text-video and textimage layouts that indicates 53.70% of the tweets (n=7065) reproduce undesirable sentiments as negative tweets, though 12.67% (n=1667) monitor optimistic sentiments such as positive tweets and 33.63% (n=4424) shows as unbiased as neutral sensitivity about the occurrence. The author proposed in [33] a significant role in communication with the consequences being controlled on various social media platforms. In this study, the applicability and effectiveness are examined with the help of ML and NLP toolkit models.…”

A Novel Approach to Classify Sentiments on Different Datasets Using Hybrid Approaches of Sentiment Analysis

“…The confusion matrix can be utilized to assess the extent to which each model has predicted true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) while assessing various models. If an algorithm outperformed the others in terms of predicting TP and TN, we used it as the foundation for our model (19)(20)(21)(22) .…”

Twitter, Instagram, Youtube Speak: Understanding Sentiments on LRT Jabodebek Services via Inset Lexicon, IndoBERT and BERTopic Approaches

“…In response to the challenges posed by the abundance of social media data, sentiment analysis becomes a relevant tool [13]. This research utilizes sentiment analysis to identify and delve into positive and negative sentiments regarding LRT Jabodebek services using comments on social media [14]. We combine Lexicon-based approaches [15], the application of IndoBERT specifically designed for Indonesian language analysis [16], and topic modelling techniques using BERTopic [17].…”