Files:
- Text cleaning and minning. Keyword extraction methods and topic modeling - 8389_s_mobley_final_code.ipynb
- Naive Bayes Classifer and Gradient Boosting Classifier - 8389_Text_Classification__models_final.ipynb
In the wake of big unstructured text data, Natural Language Processing or NLP and text analytics are on everyone’s radar. In short, NLP is the process of using artificial intelligence to understand the human language and text analysis uses NLP to carry out analysis. Whether its sentiment analysis or text mining there are multiple packages created to help data scientist and analyst along the way. Particularly in this project, we will be focused on text mining and will mostly be working with NLTK, Natural language toolkit and Regex, regular expression.Text mining includes data mining algorithms, NLP, machine learning, and statistical operations to derive useful content from unstructured formats.[5]
Part one of this project will be focused on text mining and keyword extraction news articles from the year 2020. Part two of the project will be geared more towards predictive analysis and model building.
Business Problem: Using keyword extraction to identify NASDAQ licensing pair agreement(two NASDAQ companies noted in licensing agreement) from the year 2020 by mining news articles and build a predictive model to sort for licensing articles