Analyzing Market Sentiment for Gold Commodity News Through Natural Language Processing Techniques

This study explores how sentiment analysis methods can be applied to evaluate commodity news with a specific focus on the gold market investors and traders can understand the opinions expressed in news articles by utilizing the wealth of financial news data available to them this study examines sentiment patterns in gold-related news reports using machine learning and NLP techniques it is anticipated that the research’s conclusions will provide both business communities with new information making decisions could be made easier for traders and investors if they are aware of the relationship between news, sentiment and market dynamics. In this paper, count vectorizer has been implemented for feature extraction and machine learning classifier algorithm like random forest for sentiment analysis. Gold news is categorized as having positive, negative, neutral and no sentiment. Other performance metrics like F1 Score 73%, Recall 68% and Precision 93% were calculated for the comparison of sentiment classes. Hyperparameter tuning is employed to improve the model effectiveness. The findings demonstrate a high accuracy of 86% in sentiment analysis to predict public sentiments in commodity markets which could help stakeholders develop investment strategies.