Data scraping is an important task in collecting data from the web. However, it is not imperative to collect data and not to find out how it looks using visualization. In this post we are going to analyze and visually present how the data we sraped from our previous post looks like. This post assumes that you have gone through the previous post for scraping Twitter data with Tweepy. In addition you need basic knowledge of matplotlib.

Analyzing Twitter Scraped Data

Twitter site comes with different tools that make  data accessibility very easy. It has rich libraries that can be integrated to and produce analytics for different audiences. Also Twitter provides ready made analytics for businesses which provides great business focused insights. However, in cases where your need to do complex analyses or research on social data then extracting and analyzing the data yourself gives you more control of your research and analytics.

Now let’s begin to analyze and visualize the data.

Twitter Timeline By User

Twitter Timeline By User - Analyzing Twitter Scraped Data

User Likes

User Likes - Analyzing Twitter Scraped Data

User Followers

User Followers - Analyzing Twitter Scraped Data

Retweet Time

Output

Retweet Time - Analyzing Twitter Scraped Data

Retweet Rate Pie Chart

Retweet Rate Pie Chart - Analyzing Twitter Scraped Data

Retweet Rate Line graph

Output

Retweet Rate Line graph - Analyzing Twitter Scraped Data

Conclusion

Twitter is among the top leading social media site. It allows its users to communicate to each other via short messages commonly referred to as tweets. Users can also share multimedia files such as images and videos. I this post we have analyzed the data that we collected in the previous post.We have created different visualizations from the data. This post just scratched the surface on the possibilities that can be done with the Twitter data. There are many interesting tasks of text analytics that we have not touched. However, with this basic knowledge you can easily explore in depth use cases such as detecting rumors, sarcasm, classifying tweets and clustering Twitter users based on different variables.

Analyzing Twitter Scraped Data

Post navigation