Sentiment Analysis | IJACSA

Sentiment analysis, also called opinion mining, is a natural language processing task that identifies and classifies the emotional tone or polarity, positive, negative, or neutral, expressed in text such as product reviews, social media posts, or survey responses. Approaches range from lexicon-based methods that score text using predefined sentiment dictionaries, to supervised machine learning classifiers, to deep learning models including recurrent neural networks and transformer-based architectures such as BERT that capture context and sarcasm. Beyond simple polarity, aspect-based sentiment analysis identifies opinions about specific product or service features, while emotion detection extends the task to finer-grained states such as anger, joy, or frustration. Recent surveys find that large language models outperform smaller models in low-data, few-shot settings but still lag on tasks requiring structured sentiment understanding, motivating continued work on hybrid, fine-tuned approaches. Sentiment analysis supports brand monitoring, customer feedback analysis, and financial market sentiment prediction. As an open-access sentiment analysis journal, IJACSA publishes research evaluating sentiment models across languages, domains, and low-resource text corpora.

Published in International Journal of Advanced Computer Science and Applications (IJACSA) · list last refreshed October 2026