Learning Employer Reviews.
If you are looking to skim over the project without going into too much detail, you can easily access it through here.
Employers are always looking to improve their work environment, which can lead to increased productivity level and increased Employee retention level. For example, if a Company's Employees are content with their overall experience of the Company, then their productivity level and Employee retention level would naturally increase. Now, in order to improve an Employer's work environment, the Employer must first analyze their current Employer Reviews before making a decision on how to improve their work environment. However, with hundreds and thousands of Employer Reviews on review boards such as Glassdoor, this can take a significant amount of time and resource. I will be attempting to use Topic Modeling to extract all the key topics of Employer Reviews, which can be used by Employers, to make adjustments for improving their work environment.
The dataset I will be using is from www.kaggle.com.
I have also provided the direct link below if you wish to view the dataset I used to build my model:
https://www.kaggle.com/sugar34/1016project
This project was completed using Jupyter Notebook and Python with Pandas, NumPy, Matplotlib, Gensim, NLTK and Spacy.
This project is part two of Quality Control for Banking using LDA and LDA Mallet, where we're able to apply the same model in another business context. Moving forward, I will continue to explore other Unsupervised Learning techniques.