Data Analyst
• Accessed ‘Tika’ library in python to extract text of PDF and PowerPoint documents, in order to help the team to clean up and consolidate the raw data.• Applied Natural Language Processing Toolkit ‘NLTK’ library to divide big quantity of text into single words and removed the ‘stop words’ for topics analysis.• Performed sentiment analysis to extract keywords of the text and built k-means clustering model to acquire the topics of each part of the content.• Visualized the results of the topics analysis by generating Word-Cloud in Python to anticipate the topics of each paragraph and the summary of the whole text file.