Article on Analytics for Unstructured Data
Analytics for Unstructured Data
Hello Connections,
In this article we are going to learn about Analytics for Unstructured Data, before getting into the article let us first see about the topics that we are going to cover in this article.
Topics:
- What is Un-Structured Data
- How to Deal With Unstructured Data
- Examples of analysis of Unstructured data
- Demo on analysing Un-Structured Data
What is Un-Structured Data
The data that is not inserted or maintained regarding to a pre defined model and which cannot be inserted in a traditional database is called as un-structured data.
The most common type of the un-structured data is emails, videos, images etc...
How to Deal With Unstructured Data
You can take an example to see how this works, let us have a question for our self like how to develop AP (Andhra Pradesh) and now we are looking for answers to this question on the left side of the image we can see the different responses given by 10 different people as this was an open question we will not be able to analyse the answer's properly, In order to analyse this answer we can list all the answers but if the responses are more than 10,00,000
Think how difficult is it to read through the 10 lakh responses in order to understand the peoples feeling towards this question. So, in order to deal this kind of the questions we will use machine learning...
No Problem -- I will explain this really simple. Don't worry we will stay to simple demo's rather than going to complete depth. There will be link's attached at the end of this article if you like to go for coding part of this article.
In order to analyse the responses we will code the responses and then count the different counts of the themes, in this way we will be able to get an overview of the responses and can easily analyse the data.
Examples of analysis of Unstructured data
There are a lot of examples where we use the analysis of the un-structured data, one of such examples is sentiment analysis.
so what is sentiment analysis, Sentiment analysis is the process of detecting positive or negative sentiment in text. It’s often used by businesses to detect sentiment in social data, gauge brand reputation, and understand customers.
It helps in maintaining product quality and to know what people think about the product and improve the customer satisfaction.
Let us now move on to the demo section of the article now,
Demo on analysing Un-Structured Data
In this demo we will be collecting different tweets from twitter and will try to analyse the sentiment of the tweets to understand how is analysis of the un-structure data is done.
we will first import the necessary libraries that are needed to make text analysis and then we will complete the analysis for the unstructured data:
have a look at how it is done in the below video:
Use the link to find the entire ppt as a presentation:
