Session 7 HW Assignment

Hi all,

Pls find on LMS a folder titled 'Session 7 HW' with a set of files inside.

• This HW (along with the next one for Sessions 8) will be due on midnight 6-Jan-2013 - the last day before the new term starts.
• Both these HWs are PPT based, using the same submission format as earlier MKTR assignments.
• My advice is not to wait for the last minute, to collaborate with peers and submit early.
• Reminder: R portion can be shared with peers, but write-up and interpretation should be individual only.

The Qs for the Session 7 HW are:

Reading Based HWs:

Reading 1:"How ‘social intelligence’ can guide decisions"

Q1. Summarize the main points the article makes.(in <30 words, in bullet points, font 20 on your PPT).

Q2. List some real-world examples of how social media has changed the marketing intelligence cycle.(in 1 slide max, in bullet points, font 20 on your PPT).

Q3. List any three functions that the social-intelligence toolkit replaces in the traditional toolkit. Give one real-world example for each function you list (exclude examples already in the reading).(in <30 words, in bullet points, font 20 on your PPT).

********************************

Reading 2: "Big Data, Big Ruse"

Q4. Summarize the main points the article makes (in <30 words, in bullet points, font 20 on your PPT).

Q5. With respect to the main points raised in the article, how does an open-source, no-frills analysis platform (i.e. R, basically) compare to commercial BI platforms? Pls take a stand (doesn't necessarily have to be pro-R) and argue your case. (in <30 words, in bullet points, font 20 on your PPT).

******************************

Text and Sentiment Analysis: Homework

I've putup some 85 user reviews of the the xbox 360 and the Sony Play Station 3, pulled from Amazon into xbox reviews.txt and ps3reviews.txt respectively.

The Code to execute the assignment is also putup here in R code textAnalysis.txt (its a minor variation over the classwork code). You are strongly advised to first try replicating the classwork examples on your machine, available in this blog-post, before trying this one.

Q6. Your task is to use R to text analyze the dataset. Figure out:

(i) what most people seem to be saying about each product. And thereby interpret a general 'sense' of the talk or buzz around the product.

(ii) List what positive emotions seem associated with the xbox. Likewise for the PS3. And thereby interpret what each product's strengths are. [The business implications of such early signs of Word-of-mouth, instantaneous customer feedback, buzz etc for positioning, branding, promotions, communications and other tools in the Mktg repertoire are easy to see.]

(iii) List what negative associations seem to be around. And ideate on how each product's plausible weaknesses and how it can try to defend itself. [The business importance of early warning systems, damage assessment and speedy damage control are hard to miss.]

************************************

Hypothesis Testing HW

Read in car preference ratings from G20 Infiniti data.txt into R. The G20 case background intro is available in the first couple of pages of the G20 Infiniti MEXL caselet.

The relevant R code can be found in R code hypth testing.txt. YOu are advised to refer to the class work examples as well, available in this blog-post.

Q7. Build and test the following Hypotheses (comment on what can be inferred)

(i) No significant Preference difference between Audi and Honda.

(ii) Significantly higher preference for Honda as compared to G20

(iii) Split the 1-9 rating scale into Hi/Medium/Low preference corresponding to Hi = {9,8,7}, Medium = {6,5,4} and Low = {3,2,1}.Test for whether the Hi/Med/Low preference ratings across the Ford and Pontiac are systematic or not.

(iv) Run a chisquare test similar to (iii) for G20 versus Saab's preference ratings.

In each case above, copy-paste the R output table and interpret it on the same slide.

We will solve this HW tomorrow in the proposed R tutorial. Dassit for now. For any Queries, comments, feedback etc, fel free to contact me anytime through email or the blog comments. Sudhir