A1. Visual Advertising Strategy Evaluation – Individual Report [CLO1, CLO3, CLO4]

Week 4 Thursday (June 22) 3 PM / Weighting: 20% / Length: Max 900 words

Description

This assessment provides the opportunity to critically evaluate and discuss a visual advertising strategy.

Companies or influencers change their visual advertising strategies over time. However, advertising        content managers largely rely on their gut feeling rather than quantifying the changes using objective    numeric measures. As a result, they often don’t know what they have changed and whether the changes are effective. Your job is to evaluate the changes in a visual advertising strategy using colour features.    You are also required to present and discuss your findings.

Details

Follow the below steps to complete your task:

1) Colour Usage: Divide the data into two periods. Use the cut-off date as 2019 January 1st  (i.e.,     period 1: before the cut-off date, period 2: since the cut-off date). Measures colour features      (Colorfulness, Saturation, Contrast, Clarity, Brightness, and Warm Hue) for each image using      OpenCV, which you learned during the tutorial. Report summary statistics (count/frequency,     mean, median, minimum, maximum) in a table for each color feature at each period. Also, do a visual comparison of each colour feature by choosing proper plots to see how each color feature has changed between the two periods.

2) Colour Effectiveness: Identity which color features increase viewer engagement significantly in each period. To do so, run a regression with Y = the log (like count + 1) for each period,             respectively. X variables include the above colour features and control variables about posting time: Year, Month-of-Year (January, …, December), Day-of-Week (Monday, ..., Sunday),

Time-of-day (Morning, Afternoon, Evening, Night). Interpret the regression result.

3) Colour Strategy Evaluation:

(a)  Provide related advertising posts (screenshots of both image and text description part)

from your current Instagram data to support your regression results of period 1 in the above task 2. For example, to demonstrate whether higher or lower values of color features are    better, you could compare two posts in period 1 (e.g., below or above the median value of   each color feature, respectively) that have different “like count” .

(b)  Then, based on the result of period 1 in task 2, evaluate whether the change (or no change)

between the two periods for each color feature in task 1 was proper.

(c)   Based on the result of periods 1&2, recommend effective color strategies for your company. Also, provide related advertising posts to support your arguments.

In completing this task, apply appropriate data analytics and consider the concepts introduced in class.    Make sure that your discussion component is logical, clearly structured, and professionally presented.    Your report should not exceed the word limit, excluding the title page, relevant images, tables or charts.

Title page (1 page) includes (1) the Title of your report, (2) the Word count, (3) the Course name, tutorial session and group, tutor’s name, (4) Your first and last name & zID

Submission instructions

A.   Submit your report to Turnitin via Moodle.

1)    .doc contains your report. File name: Tutorial session_Group_ your first and last name & zID _A1.doc” (e.g., W12_1_Junbum Kwon_zXXXXX_A1.doc)

B.   Submit other supporting files (data, image, paper and code) to Moodle submission folder.

2)    .xlsx file contains the dataset on which you run a regression.

3)    .ipynb contains all relevant code to get the results in your report. Make a zip file by combining all colab files.

●   For each missing file among the above (1) to (3), -1 mark

Marking Criteria

Your assignment will be marked based on the following marking criteria:

1.   Analysis: Quality of advertising data image analytics

2.    Interpretation & Recommendations: Quality of interpretation and argumentation

3.   Written Presentation: Quality of written report

For further information, see the below marking rubric.