Reference no: EM131477802
One page analysis using R I need detailed code commented with graphs and explaining what is found
Twitter Data Mining Project
Chevrolet
Understanding how consumers rank brand value is fundamental to marketing strategy. The proliferation of social media has given both marketers and consumers a data source to understand consumer perceptions; noise, the ambiguity and sheer volume of such data pose substantial challenges to algorithmic solutions. The Project will use the Python to gather tweets and clean the data so it can be statistically analyzed. The data will be collected with the REST API. Next, the using the MASS package in R which organizes brands according to how consumers rate them on attributes (Green et al. 1989, Shocker and Srinivasan 1979, Steenkamp et al. 1994).
This project is using the Chevrolet and a perceptual attribute hunting, fishing and outdoors; the goal is to develop and assign a score to the brand, a high score will indicate a perceived relationship that is strong between the brand and the attribute. This approach relies on the notion of the attribute exemplar. The exemplar in this project is Chevrolet, and this project will demonstrate whether it is strongly affiliated with the fishing attribute. Given Chevy Trucks Twitter handle, and a search query representing an attribute of people that enjoy fishing, hunting, and outdoors. First, we collect exemplar tweets representing the hunting, fishing and/or outdoor hastags, then analyze the function between the followers of Chevy Trucks and the exemplars hunting, fishing, and outdoors, and finally those of the brand.
The question we are looking to answer is how strong is the correlation of the brand Chevrolet and hunting, fishing and outdoors. We will learn if the brand is heavily aligned with the attributes of hunting, fishing, and the outdoors. Marketers will be interested in this information, this can be used for both campaign design and media channel selection.
I need a detail statistical analysis of the csv attached with summary statistics, graphing and a well commented code. I also need a explanation of why everything was performed and a explanation in layman's terms that explains what was found.
Why would you graph bow hunting when hunting had the largest result set?
Attachment:- output Demarest.csv