Industry : Politics
Various Steps for Sentimental Analysis:
- Creating the text data from various UCI repository .
- Create the corpus and convert into structural data.
- Tokenize the structural data using various NLP packages.
- Analyze the sentiment of token by polarity checking.
- Compare the negative and positive polarity of text and graph generation on polarity checks.
Industry : Government (Census data Set or government site data set)
- Collect the crops data of India from (2000-2015) from the government sites.
- Handling with missing Data (Using functions).
- Create the sample data using probability distribution and PCA(Principle Component Analysis).
- Analyze the data using statistical methods.
- Predictive Analysis using Artificial Neural Networks.
- Graph Visualization, state wise crop generation.
Industry : Social
- Setup a Connection as Twitter Application developer. (Using Authentication and Registration)
- Extracting twitter data by streaming process.
- Cleaning and steaming the text data using various packages.
- Generate the Word Graph and the frequency count of the words.
- Get the locations of various tweets and predicting the places that are more prominent for the terrorist activities.
- Collect the data for goods.
- Store the Data on Hadoop server.
- Applying Machine Learning (Association rule Mining) Algorithm for predication of
- Find the support and Confidence for the each product.
- Predication of goods, whose sales are affected in future.
Industry : Entertainment
- Import the text data from the various sites.
- Collect the structural data for the each IPL team.
- Analysis the text data and structural data.
- Use Statistical Inference (Linear Regression Model) system on the formatted data.
- Make a confusion matrix for the each team.
- Preparation of probability graph of each team.
- Collect the data from the shopping sites.
- Get the age of different user.
- Make a cluster of different age groups.
- Associate the shopping preference with the age group.(K-means clustering)
- Generate the cluster of different age groups with their shopping frequency of items.
- Generate the sales of items according to the season clusters.