Skip to content

Latest commit

 

History

History
10 lines (6 loc) · 2.56 KB

README.md

File metadata and controls

10 lines (6 loc) · 2.56 KB

sentimentanalysis

In this course, module, you will be working as a data analyst for Alert Analytics, a data analytics consulting firm.

On your first project for the firm, Alert's founding partner and SVP Michael Ortiz has asked you to take over for a recently-transferred analyst who has been working on a big data project for Helio, a smart phone and tablet app developer. Helio is working with a government health agency to create a suite of smart phone medical apps for use by aid workers in developing countries. The government agency will be providing workers with technical support services, but they need to limit the support to a single model of smart phone and operating system. This will also help to limit purchase costs and ensure uniformity when training aid workers to use the device. After completing an initial investigation, Helio has created a short list of devices that are all capable of executing the app suite's functions.

To narrow this list down to one device, Helio has engaged Alert Analytics to conduct a broad-based web sentiment analysis to gain insight into the attitudes toward the devices. Your job is to conduct this analysis.

First, you will set up and become familiar with the Amazon Web Services (AWS) computing environment. Next, you will use the AWS Elastic Map Reduce (EMR) platform to run a series of Hadoop Streaming jobs that will collect large amounts of smart phone-related web pages from a massive repository of web data called Common Crawl. Once this data has been gathered, you will then compile it into a data matrix where you can then use a machine learning package called WEKA or the statistical programming language R to develop a predictive model that will label the data with the web sites' sentiment toward the devices. You will then apply your model to the data using either tool. Finally, you will prepare a presentation and summary of your findings from the analysis for an executive audience and report on lessons learned during the process.

After you complete the Helio project, Michael Ortiz needs your help to evaluate a potential project for a high-end department store chain. Recently the chain launched a store-within-a-store concept targeted at fashion-conscious young women. The buyer of this concept store is considering adding a number of new brands to the store's collection. She has asked for insight into consumer sentiment on the web towards these brands to help her make purchasing and marketing decisions. Your job is to evaluate the buyer's information needs and manage her expectations of what sentiment analysis can and cannot accomplish.