I have been leaning on how to do Text Analytics and Natural Language Processing on wide platform of social media like Public Forums (Edmunds, Yelp etc.), Instagram, Twitter etc.
This is the first Project of the Series #User-Generated-Content-Analysis. Since this is a learning process, you will see a gradual improvement in the techniques used and also reduction in the number of assumption.
As for this project:
Things Learned:
- Lift Calculation
- Word-Frequency count
- Natural Language Processing
- Stemming & Lemitization
- Importance of word replacement
- Sentiment Analysis
- Cosine Similarity
- Topic Modelling
The Indian Premier League (IPL), officially Vivo Indian Premier League for sponsorship reasons, is a professional Twenty20 cricket league in India contested during April and May of every year by teams representing 18 Indian cities and some states. The IPL is the most-attended cricket league in the world. There have been eleven seasons of the IPL tournament. The aim of this project is to calculate the worth of player based on their past performance and popularity among the crowd.
The flow of this project goes as:
-
To get the historic data from official IPL Website for past 5/10 years. This is done mainly to get the quantitative standpoint and the player's performance trend over the past years. This will be one of the key factor in calculating the player's worth as the performance is one of the key factors in determining the player's worth.
-
Since the historic data has so many columns, it is important to get the right data from it. Once this is done, the next step is to get the data from Twitter. This is done by using vasious search queries like: #IPL, #Vs, #PlayerName.
-
Once we have all this data, the aim is to find midway between the quantitative data and qualitative data.
The notebook is commented to show all other steps.