EMOTIONAL DETECTION ON SOCIAL MEDIA USING AI: A CASE STUDY OF X (FORMERLY TWITTER)

Main Article Content

FAISAL ALTHOBAITI

Abstract

The advent of the digital era increased the use of social media platforms such as X, which has also become a platform where humans express their emotions and generate a large volume of complex emotional data. This research explores artificial intelligence (AI) applications, especially natural language processing (NLP), for emotion detection in text on social media platforms. Advanced classifiers like SVM, RNN, LSTM, CNN, and GRU are used to study the performance and identify emotion spectrums beyond binary sentiment analysis. Comparative analysis of before and after optimization outcomes shows the significance of hyperparameter tuning and cross-validation in enhancing the model metrics like accuracy and F1-score. GRU is the top after post-optimization, with 93.10% accuracy and outstanding generalization. On the other hand, CNN is also strong, with 92.44%. Based on this, the significance of optimization techniques is figured out. Thus, GRU and CNN are optimal options for emotion detection on X because the platform gives strong support to mental health, marketing and public sentiment analysis.


Keywords—Emotional Detection, Social Media, Natural Language Processing (NLP), Sentiment Analysis, Deep Learning, RNN, CNN, GRU, Hyperparameter Tuning, Cross-Validation.


 

Downloads

Download data is not yet available.

Article Details

Section
Articles