International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 06 | Jun 2025
p-ISSN: 2395-0072
www.irjet.net
Artificial Intelligence for Analyzing Sentiment Analysis in Digital Exchanges Prakhar Singhal1, Pawan Kumar2, Ms. Aarushi Thusu3 1Noida Institute of Engineering and Technology, Greater Noida, UP, India 2Noida Institute of Engineering and Technology, Greater Noida, UP, India 3 Assistant Professor, Department of computer science and engineering,Noida Institute of Engineering and Technology, Greater Noida, UP, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract With the exponential rise in social media engagement, understanding public sentiment from online content has become critical for industries, governments, and researchers. This study explores the application of artificial intelligence techniques for sentiment analysis of Twitter data. Using the Sentiment140 dataset, we compare traditional machine learning models such as Logistic Regression and Support Vector Machines with deep learning approaches like LSTM. Additionally, we discuss the integration potential of transformer-based models like RoBERTa. The paper outlines preprocessing techniques, feature extraction strategies (TF-IDF and GloVe), and evaluates models based on accuracy, precision, recall, and F1-score. Our results show that deep learning models outperform classical methods, with significant improvements noted in LSTM's handling of sequence data.
Key Words: Sentiment Analysis, NLP, Twitter, LSTM, Machine Learning, Deep Learning, GloVe, TF-IDF, RoBERTa. 1. INTRODUCTION Social media platforms, particularly Twitter, have become rich sources of opinionated data. Extracting insights from such data allows stakeholders to make informed decisions in marketing, politics, crisis management, and more. Sentiment analysis, a subfield of Natural Language Processing (NLP), focuses on classifying text as positive, negative, or neutral. This study applies AI and ML models to evaluate sentiment from a large-scale tweet dataset. Twitter's brevity and real-time nature make it both a challenging and an attractive medium for sentiment analysis. Unlike longer texts, tweets often contain abbreviations, slang, emoticons, and hashtags, making them complex for traditional rulebased systems. With the development of AI and neural language models, it has become feasible to understand and classify these informal texts accurately. This paper aims to design and evaluate several models—ranging from classical machine learning to deep learning—on the Sentiment140 dataset. We highlight their comparative strengths, propose potential improvements, and discuss the social and ethical implications of automated sentiment detection.
2. LITERATURE REVIEW The evolution of sentiment analysis techniques reflects a progression from traditional machine learning to deep learning and transformer-based models. Pang and Lee (2008) used Naive Bayes and SVM for movie review sentiment classification, highlighting the importance of feature engineering. Go et al. (2009) proposed distant supervision using emoticons for labeling tweets. Pak and Paroubek (2010) focused on a two-stage approach to classify subjective/objective tweets. Kouloumpis et al. (2011) emphasized the role of informal elements like hashtags and emoticons in improving accuracy. Deep learning models like CNNs by Severyn and Moschitti (2015) and transformers like BERT (Devlin et al., 2019), RoBERTa (Liu et al., 2019), and XLNet (Yang et al., 2019) marked a leap in contextual understanding and classification performance.
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 876