Mastering Marketing Data Science

EXERCISE 7.1: SOCIAL NETWORK ANALYSIS (SNA) IN MARKETING

Objective: To understand the application of social network analysis in identifying influential users in a marketing context.

Tasks:

1. Visualize the Social Network:
   • Use networkx to create a visual representation of the network.
   • Highlight key nodes that might represent influential users.
2. Calculate Centrality Measures:
   • Calculate degree, betweenness, and eigenvector centrality for each node.
   • Identify top five influential users based on these centrality measures.
3. Discussion:
   • Discuss how these measures can help in identifying potential influencers for marketing campaigns.
   • What are the limitations of this approach?

Steps:

1. Load the Data and Import Libraries:

   1. import matplotlib.pyplot as plt
   2. import networkx as nx
   3. sna_data = pd.read_csv("/data/Social_Network_Analysis_Data.csv")

   This line imports the matplotlib and networkx library and loads the social network data from the CSV file into a pandas DataFrame.

2. Create the Graph:

   4. G = nx.Graph()
   5. for index, row in sna_data.iterrows():
   6. G.add_node(row[‘User’], followers=row[‘Followers’], engagement_rate=row[‘Engagement Rate’])

   Here, we create an empty graph using networkx and then add nodes (users) from the DataFrame. Each node is added with attributes ‘followers’ and ‘engagement_rate’. The graph currently has 25 nodes. Here are the attributes for the first five nodes:

   • User 0: 2,832 followers, 5.93% engagement rate
   • User 1: 3,364 followers, 6.03% engagement rate ...