TWEETING SENTIMENTS ANALYZING AND COMPARING THE EMOTIONAL PATTERN VARIANCE OF TWO USERS IN TWITTER POSTS.

Abstract

Twitter has developed into a potent platform for expressing one's feelings and opinions in real time in the age of digital communication. This work explores and compares the emotional patterns of two distinct Twitter users by analyzing the sentiment and emotional content embedded in their tweets.  Utilizing natural language processing (NLP) techniques and sentiment analysis tools, we extracted emotional cues.  We classified the tweets as positive, negative, neutral, and emotion-specific types like joy, anger, sadness, and fear.  The emotional variance was quantified over time to observe patterns, trends, and shifts in mood or response to external events.  By employing visualizations and statistical comparisons, the research work reveals notable differences and similarities in emotional expression, frequency, and intensity between the two users.  This comparative approach not only provides insights into individual emotional behavior on social media but also contributes to broader applications such as digital psychology, influencer profiling, and social media monitoring.  The implementation of the proposed model provides a good performance concerning memory and time.  This research work demonstrates the importance of the sentiments of human beings; their new technologies, future sentiment analysis research should be enhanced even more.