This data mining project utilizes the NewsAPI to fetch recent articles on a user-specified topic. It then applies sentiment analysis using TextBlob to determine the overall sentiment of the news coverage. The results are presented through an intuitive web interface, showcasing the average sentiment score and a distribution of positive, neutral, and negative sentiments across the articles.

During the development of this News Sentiment Analysis project, several challenges were encountered which required innovative solutions. One of the primary obstacles was processing large volumes of text data efficiently, which it was overcome by utilizing pandas for fast data manipulation and analysis. This allowed to handle numerous news articles quickly and extract meaningful insights. Another significant challenge was presenting complex sentiment data in an easily understandable format for users who might not be familiar with data analysis. To address this, I implemented clear visualizations, including pie charts and sentiment bars, along with explanatory text. This approach made the sentiment analysis results more accessible and intuitive, enabling users to grasp the overall sentiment of news coverage on their chosen topic at a glance.