ML based Text Summarization for Sentiment Analysis in Information Retrieval using Feature Engineering

Sentiment analysis plays a crucial role in understanding user preferences and opinions in the field of information retrieval. This research focuses on developing a system that combines text summarization and machine learning techniques to improve sentiment analysis accuracy. The proposed approach employs extractive and abstractive summarization techniques to reduce lengthy texts into concise summaries while preserving key information. Feature engineering is then applied to extract sentiment-related elements from the summary text, providing valuable insights for the SVM model. The SVM model, enhanced with feature engineering, is expected to effectively summarize text and accurately detect sentiments expressed in documents. This research contributes to the advancement of sentiment analysis techniques and provides valuable insights for decision-making and content development.