Digital Marketing effectiveness of a brand through Facebook

PGP/33/007 AJMAL HUSSAIN || PGP/33/099 VINITA SINGH || PGP/33/136 RAMAKRUSHNA HAIBRU || PGP/33/187 PATIL JAYESH ASHOK
PGP/33/246 SOURABH MAHAJAN || PGP/33/263 ANURAG || PGP/33/333 MAKKA SHIVA KUMAR

Abstract

The research will be dedicated to involve the data science approach to predict the performance metrics of posts published on brands’ Facebook pages and understand the impact of these posts on consumer engagement and brand building. The motivation for the choice of the topic is the proliferation of social media as the biggest influencer for expression and value creation for the customers. Since Facebook is the most powerful social media platform to exchange ideas and spread awareness about the brand, companies utilize it to drive their marketing communications and make strategic decision for brand building by keeping track of their customers’ interactions with the brand posts.

Motivation for the choice of research topic

Social media has become the biggest influencer for expression and value creation for the customers. Since Facebook is the most powerful social media platform to exchange ideas and spread awareness about the brand, companies want to keep track of their customers’ activities to drive the marketing communications and make strategic decision for brand building.

Dataset

The dataset contains the columns related to users’ engagement and interactions with the posts on brands’ Facebook page. It is a mix of factor, char, numeric data-types.

fbstore.df = read.csv(file="G:/My Drive/Term V/DAM 2018/Project/Data Sets/FB/FB.csv",header=TRUE, sep=";")
str(fbstore.df)
## 'data.frame':    500 obs. of  19 variables:
##  $ Page.total.likes                                                   : int  139441 139441 139441 139441 139441 139441 139441 139441 139441 139441 ...
##  $ Type                                                               : Factor w/ 4 levels "Link","Photo",..: 2 3 2 2 2 3 2 2 3 2 ...
##  $ Category                                                           : int  2 2 3 2 2 2 3 3 2 3 ...
##  $ Post.Month                                                         : int  12 12 12 12 12 12 12 12 12 12 ...
##  $ Post.Weekday                                                       : int  4 3 3 2 2 1 1 7 7 6 ...
##  $ Post.Hour                                                          : int  3 10 3 10 3 9 3 9 3 10 ...
##  $ Paid                                                               : int  0 0 0 1 0 0 1 1 0 0 ...
##  $ Lifetime.Post.Total.Reach                                          : int  2752 10460 2413 50128 7244 10472 11692 13720 11844 4694 ...
##  $ Lifetime.Post.Total.Impressions                                    : int  5091 19057 4373 87991 13594 20849 19479 24137 22538 8668 ...
##  $ Lifetime.Engaged.Users                                             : int  178 1457 177 2211 671 1191 481 537 1530 280 ...
##  $ Lifetime.Post.Consumers                                            : int  109 1361 113 790 410 1073 265 232 1407 183 ...
##  $ Lifetime.Post.Consumptions                                         : int  159 1674 154 1119 580 1389 364 305 1692 250 ...
##  $ Lifetime.Post.Impressions.by.people.who.have.liked.your.Page       : int  3078 11710 2812 61027 6228 16034 15432 19728 15220 4309 ...
##  $ Lifetime.Post.reach.by.people.who.like.your.Page                   : int  1640 6112 1503 32048 3200 7852 9328 11056 7912 2324 ...
##  $ Lifetime.People.who.have.liked.your.Page.and.engaged.with.your.post: int  119 1108 132 1386 396 1016 379 422 1250 199 ...
##  $ comment                                                            : int  4 5 0 58 19 1 3 0 0 3 ...
##  $ like                                                               : int  79 130 66 1572 325 152 249 325 161 113 ...
##  $ share                                                              : int  17 29 14 147 49 33 27 14 31 26 ...
##  $ Total.Interactions                                                 : int  100 164 80 1777 393 186 279 339 192 142 ...

The dataset contains metrics which can be categorized in following categories:

  1. Features that identify a post - Post_Features.
  2. Actual content of the post - Content.
  3. Performance and reach of the post - Performance.
  4. Characteristics of the post - Categorization.

The data set can be found here.

Methodology for Data Analysis

CRISP-DM will be used as a basic framework to build a predictive model for the brand.
Coding language: R
IDE: RStudio
image:

Research objective

The following objectives are intended to be achieved through the project.

  • Determine the engagement pattern of users’ on FB posts based on post type, month, hour and day of publishing.
  • Define performance metrics for the brand page.
  • Relation of the interaction factors with the performance of the brand post by running correlation tests and understand the significance of each factor for brand building
  • Testing the hypothesis that type of post affects its impact on the consumer
  • Building a model for making posts viral/ reach maximum users

Managerial insights to be gained

Based on analysis of the data, the following insights can be gained:

  • Understanding the role of social media in brand building
  • Understanding the social media impact created by:
    • Type of post(Links, Photos, Videos, Statuses)
    • Timing of the posts
  • Identifying the performance metrics for the posts to drive the brand building strategy
  • Using analytics models to develop social media campaigns for further product launches and other brands.