International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
SentimentPro: AI-Powered Social Media Sentiment Analysis On Twitter Data Akanksha Borhade 1, Aishwarya Sangle2, Sakshi Patil3, Dr Vipin Borole4 1 Master of Computer Application, MET’s Institute of Management, Bhujbal Knowledge City, Nashik, India
2 Master of Computer Application, MET’s Institute of Management, Bhujbal Knowledge City, Nashik, India
3 Master of Computer Application, MET’s Institute of Management, Bhujbal Knowledge City, Nashik, India
4 Professor, Master of Computer Application, MET’s Institute of Management, Bhujbal Knowledge City, Nashik,
India ---------------------------------------------------------------------***--------------------------------------------------------------------1.1 Literature Review Abstract - This paper presents SentimentPro, an AI system that analyzes Twitter data in real time to help businesses track how their brand is perceived. Tweets are collected using the Twitter API, then cleaned and processed with transformer models to determine if the sentiment is positive, neutral, or negative. The results from past analysis are saved in a MySQL database, and interactive dashboards show these findings visually to help with making informed business decisions. SentimentPro uses supervised learning, natural language processing, and data from outside sources to create a flexible, real-time solution for monitoring trends in business.
1.Sentiment Dictionaries: Sentiment dictionaries build on word lists by adding more details like how strong a feeling is, the use of emojis, and phrases made of more than one word [3]. This helps a lot with platforms like Twitter where people express themselves in many different and creative ways [4]. Many of these dictionaries are now kept up to date through group efforts or using computer programs that learn automatically. This makes them more flexible and better at keeping up with new ways people use language compared to fixed word lists.
Key Words: Sentiment Analysis, Twitter Data, Transformer Models, Business Intelligence, Data Visualization.
2. Machine Learning Models: Traditional methods like Naïve Bayes, Logistic Regression, and Support Vector Machines (SVM) learn from examples that have already been labeled and usually work better than just using word lists on most tests [5]. As deep learning has become more popular, models like CNNs, LSTMs, and transformer-based models such as BERT and RoBERTa have been developed. These models understand the connections between words and their surroundings better, making them very effective at handling short texts like tweets [6], [7].
1.INTRODUCTION Social media sites, especially Twitter, are important places where people share their opinions and feedback right away [1]. Companies use this information to understand how their brand is seen, check how well their campaigns are working, and predict what might happen in the market. But tweets are short, often use casual language, and can be hard to understand, which makes it tough to accurately figure out people's feelings from them. SentimentPro helps with this by using a full process that includes cleaning up text, using advanced language models, storing data securely, and showing results through easy-to-use dashboards. Twitter's tweets are short, use informal language, and vary a lot, which makes it hard to do sentiment analysis [2]. SentimentPro tackles these problems by using strong text cleaning, the best language models, and dashboards that make it easy to see the results. This study looks to solve these issues by creating a solid way to analyze emotions in tweets, which helps businesses understand trends. The main goals are to correctly categorize tweets about products or services as positive, negative, or neutral, and to look at how overall customer feelings change over time. By doing this, the research hopes to give businesses useful and timely information that can help shape their marketing plans, improve how they connect with customers, and gain an edge in the fast-moving online world [2].
© 2025, IRJET
|
Impact Factor value: 8.315
3. Natural Language Processing (NLP): NLP techniques rely on machine learning, especially statistical learning. These methods use a general learning algorithm along with a large collection of text data, called a corpus, to understand and learn language rules [5]. Sentiment analysis, which is a part of NLP, has been studied at different levels. It started as a way to classify whole documents, then moved to sentences, and now even to phrases [11]. NLP is a branch of computer science that helps computers understand and interpret human language, allowing them to interact with the real world. 4. Support Vector Machine: SVM is language independent but uses a format that is familiar to programmers who work with C-family languages like Python. However, the size of the output depends on how
|
ISO 9001:2008 Certified Journal
|
Page 126