Integrating Sentiment Analysis into AI-Driven Budgeting: Advancing Personal Financial Management through Emotion-Aware Financial Insights - Natural Language Processing - Sentiment Analysis

Sabbavarapu, Ravi Kumar (2025) Integrating Sentiment Analysis into AI-Driven Budgeting: Advancing Personal Financial Management through Emotion-Aware Financial Insights - Natural Language Processing - Sentiment Analysis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study aims to integrate sentiment analysis models within AI-driven budgeting systems to enhance emotion-aware financial guidance. Methods involved embedding Random Forest, AdaBoost, Deep Neural Network, and LSTM classifiers into a budgeting framework, with TFIDF vectorisation for machine learning models and tokenisation with embedding’s for deep learning models on a balanced dataset of financial news headlines. Findings indicate that the LSTM model achieved the best balance of precision and recall across bearish, bullish, and neutral sentiments, while the Random Forest classifier delivered high precision but low recall for minority classes, AdaBoost underperformed, and the Deep Neural Network yielded moderate improvements. Limitations include vulnerability to class imbalance, misclassification of sarcasm and domain-specific jargon, and high computational requirements for training. Future research should explore transformer-based architectures with domain-adapted embedding’s, adaptive sampling techniques, and sarcasm detection modules to improve accuracy and efficiency. Integration confirms sentiment signals can be effectively mapped into budgeting rules.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Thomas, Lavish UNSPECIFIED
Uncontrolled Keywords:	Sentiment analysis; AI budgeting; LSTM; Financial forecasting
Subjects:	H Social Sciences > HG Finance Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	12 Aug 2026 10:00
Last Modified:	12 Aug 2026 10:00
URI:	https://norma.ncirl.ie/id/eprint/9514

Actions (login required)

View Item