DATA MINING AND TWITTER By Kylie Wyman. WHAT IS DATA MINING? Data mining is the practice of searching through, and collecting, large amounts of data.

DATA MINING AND TWITTER

By Kylie Wyman

WHAT IS DATA MINING?

Data mining is the practice of searching through,

and collecting, large amounts of data in order to find

useful patterns or trends. One of the sole purposes

of data mining is to discover relationships within the

data that is found on different databases.

TWITTER

In 2013, Twitter sold data of users for $47.5 million to companies that

“analyze the data for insights into news events and trends.” (Dwoskin, 2013)

Companies pay Twitter for access to torrent of tweets from the service’s

215 million monthly active users. (Luckerson, 2013)

Companies such as DirecTV use Twitter data in order to spot power outages

based on customer complaints. (Dwoskin, 2013)

Twitter has minimized the amount of data that outside firms are allowed to

pull from its system free of charge.

The Red Cross USED Twitter after Hurricane Sandy to pinpoint where aid

was needed the most.

WHY DO COMPANIES USE DATA MINING?

Companies/Websites use data mining in order to

collect data from people who visit their sites.

Companies aggregate data in order to determine

how a product will do in the market, or come up with

new advertising campaigns

HOW DO THEY DO IT?

Description and Prediction

Anomaly detection  - What data trends look like in a typical case.

Stats are used to determine if something is notably different.

Association learning: Seeing what users buy online and making

suggestions for future purchases. (IE: Buying a book on Amazon and

having the website suggest an author next time you make a

purchase).

Cluster detection:  Recognizing distinct clusters or sub-categories

within data. (IE: Classifying Internet users into groups.)

Classification: Adds more information to categories.

PROTECTING YOURSELF FROM DATA MINING

Never provide more information than what is required by the

retailer when making an online purchase.

Seek out websites that show you how to maximize your privacy

settings.  

Use browser plug-ins, proxy servers, or pay services that hide your

computer’s individual IP address. 

Adjust the privacy settings on your Internet browser to block third-

party “cookies” 

(Your Life In Pixels, 2013)

REFERENCES

Dwoskin, E. (October, 2013 7). Twitter's data business proves lucrative. Retrieved on Dec 1,

2013 from http://

online.wsj.com/news/articles/SB10001424052702304441404579118531954483974

Furnas, David. The Atlantic, (2012). Everything You Wanted to Know About Data Mining but

Were Afraid to Ask. Retrieved from Dec 1, 2013 http://

www.theatlantic.com/technology/archive/2012/04/everything-you-wanted-to-know-about-data-

mining-but-were-afraid-to-ask/255388

Green, A. (JUNE, 2012). Twitter API programming tips, tutorials, source code libraries and

consulting. Retrieved from Dec 2, 2013 http://

140dev.com/twitter-api-programming-blog/category/data-mining-tweets/

Luckerson, V. (October, 8 2013). Twitter is selling access to your tweets for millions read

more: Twitter is selling access to your tweets for millions Retrieved from

http://business.time.com/2013/10/08/twitter-is-selling-access-to-your-tweets-for-millions/

Data mining, 2013. In Merriam-Webster.com. Retrieved Dec 5, 2013 from

http://www.merriam-webster.com/dictionary/data%20mining

REFERENCES

Meyer, David. CNN, (2013). A Plan to Mix Privacy into Data Mining. Retrieved Dec 1, 2013

from http://money.cnn.com/2013/10/28/smallbusiness/data-mining/

Mims, C. (October, 13 2010). How to use twitter for personal data mining. Retrieved Nov

29, 2013 from http://www.technologyreview.com/view/421201/how-to-use-twitter-for-

personal-data-mining/

Waxer, C. (October, 2013 28). How data mining can boost your revenue by 300%. Retrieved

Nov 28, 2013 from http://money.cnn.com/2013/10/28/smallbusiness/data-mining/

“Your Life in Pixels.” (May, 2012 7). Retrieved Dec 3, 2013 from http://www.aarp.org/home-

family/personal-technology/info-05-2012/video-data-mining-internet-privacy-ines.html