International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 02 | Feb 2026
p-ISSN: 2395-0072
www.irjet.net
ADVANCED APPROACHES IN SENTIMENT ANALYSIS: FROM FEATURE SELECTION TO EMOTION DETECTION Mrs. D. Kavitha1,Mohammed Jawad2, K.Nandhan Kumar3, B.NISHANTH4, V.PAVAN KUMAR5 1Assistant Professor, Department of IT, TKR College of Engineering and Technology, Telangana, India 2,3,4,5B.Tech Students, Department of IT, TKR College of Engineering and Technology, Telangana, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Sentiment analysis and emotion detection play a
systems. Early studies proved that machine learning methods can effectively classify sentiments from text using supervised approaches [1]. Later, opinion mining became a major research domain and was recognized as an essential technique for extracting valuable insights from large volumes of unstructured data [2].
vital role in modern Natural Language Processing (NLP) by enabling organizations to understand user opinions, feedback, and emotional responses from textual data. Most traditional sentiment analysis approaches depend on labelled datasets and supervised machine learning models, which reduces flexibility and requires frequent retraining when applied to new domains. To overcome these limitations, this project proposes a web-based Sentiment and Emotion Classification System using the Gemini Large Language Model (LLM) for zero-shot text analysis.
1.1 Need for Sentiment and Emotion Analysis In modern digital platforms, users continuously generate text data in the form of reviews, comments, tweets, and feedback. Analysing such large-scale text manually is impractical. Sentiment analysis helps in understanding overall public opinion, while emotion detection provides deeper insight by identifying emotional states such as joy, anger, sadness, fear, and surprise. Traditional systems mainly focus on polarity classification and often fail to capture fine-grained emotions, reducing the depth of analysis [2].
The system accepts unlabelled CSV datasets and performs automated preprocessing such as text cleaning, normalization, and noise removal. Each text instance is analysed using Gemini to predict sentiment polarity (Positive, Negative, Neutral) and emotion categories (joy, sadness, anger, fear, surprise, disgust, neutral) without any prior training. The platform also supports real-time single-text classification through an interactive web interface.
1.2 Limitations of Traditional Approaches Most conventional sentiment analysis systems rely on rulebased techniques or supervised machine learning models such as Naive Bayes, SVM, and Logistic Regression [1], [2]. These approaches require large labelled datasets, extensive feature engineering, and frequent retraining when applied to new domains. Even modern transformer-based deep learning models such as BERT improve contextual understanding [3], but still require domain-specific finetuning and labelled training data, which increases computational and maintenance cost.
To improve interpretability and insight, the system generates multiple visualizations including sentiment distribution charts, emotion frequency plots, confidence density graphs, word clouds, scatter plots, and aspect-based sentiment analysis. Additionally, a pseudo-SHAP based explanation mechanism is integrated for single-text analysis to highlight word-level importance and improve transparency. Developed using Django and modern visualization libraries, the proposed system provides a scalable, domain-independent, and userfriendly solution for sentiment and emotion analysis in realworld applications.
1.3 Emergence of Large Language Models
KEYWORDS- Sentiment Analysis, Emotion Detection, Gemini LLM, Zero-Shot Classification, Django, NLP, Visualization, Explainable AI, PseudoSHAP
Recent advancements in Large Language Models (LLMs) have significantly improved NLP capabilities by enabling zero-shot and few-shot learning. Models such as GPT demonstrated that language models can perform classification tasks without explicit training on labelled datasets [4]. Similarly, Google’s Gemini model provides highly capable LLM-based reasoning and text understanding, making it suitable for sentiment and emotion analysis in a domain-independent manner [5]. This shift enables systems to analyse new datasets without retraining and improves adaptability to different text styles and domains.
1. INTRODUCTION Electric Sentiment analysis is one of the most important research areas in Natural Language Processing (NLP), focused on identifying human opinions, attitudes, and emotional responses expressed in textual form. It is widely applied in customer feedback analysis, product review mining, social media monitoring, and business intelligence
© 2026, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 521