***********************************************
This work is a copyright of ABV-IIITM students:
Abhisek Anjana (IPG2014001)
Akshit Agarwal (IPG2014008)
Ayush Gupta (IPG2014026)
***********************************************

**Please note that the actual report for the research is not uploaded due to copyright issues, please refer to the presentaion pdf to know the details of the research done.

Set up the Environment:
1. From the dependicies folder install the pycharm software and python.
2. Install the mentioned Libraries via pycharm.

Run the code:
1. Open and run the WebScrapeThreads code file given in the Code folder via pycharm. This will download the reviews in a text file.
2. Open and run the polarity file or polarity_english(location) file based on what reviews who have downloaded. This will divide the reviews into good and bad, based on their ratings and polarity.
3. Open and run the partOfSpeechTagging to remove the extra words from the reviews.
4. Now break the reviews into words using tokennization method via linux terminal.
5. Proceed to complete text link analysis, using unigram and bi-gram search in order to obtain patterns.
6. Collect the relevant words and their frequencies, and then cluster those into similar categories so in order to create word clouds.