News Tone, University of Adelaide, South Australia, 02/01/20, 06/01/20, Developed an advanced sentiment analysis tool to evaluate the tone of news articles, employing AI and machine learning techniques to provide insights into public opinion and media bias., Python, Data Collection: Scraped and compiled a diverse dataset of news articles from various online sources using web scraping tools like BeautifulSoup and Scrapy., Data Preprocessing: Conducted comprehensive data cleaning and preprocessing tasks, including text normalization, tokenization, lemmatization, and removal of stop words., Feature Engineering: Extracted relevant features such as word frequencies, sentiment lexicons, and syntactic dependencies to enhance model performance., Model Development: Implemented and fine-tuned machine learning models (e.g., Naive Bayes, SVM) to classify the sentiment of news articles into categories like positive, negative, and neutral., Performance Evaluation: Assessed model accuracy, precision, recall, and F1-score, employing cross-validation techniques to ensure robustness and generalizability., Visualization and Reporting: Designed interactive visualizations using Matplotlib and Seaborn to present sentiment trends and patterns, facilitating user interpretation and decision-making., Technical Proficiency: Deepened expertise in natural language processing and machine learning, mastering techniques essential for text analysis and sentiment classification., Project Management: Demonstrated strong project management skills, successfully coordinating tasks within a team, adhering to deadlines, and managing resources efficiently., Collaboration and Communication: Enhanced teamwork and communication skills by collaborating with peers, presenting findings, and integrating feedback to refine the project., Analytical Thinking: Developed critical analytical skills, enabling the identification of biases and patterns in news media, contributing to a better understanding of public sentiment.