Scribd
Upload
4 views2 pages

Jaccard Similarity in Social Networks

The lab assignment focuses on implementing the Jaccard Similarity Index to analyze user similarities based on shared friends in a social network. It includes tasks for calculating the index, parsing user data, and interpreting results to identify high-similarity user pairs. The implications of these findings include friendship recommendations, community detection, and insights into influence within social networks.

Uploaded by

lamya.gandhi4
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views2 pages

Jaccard Similarity in Social Networks

The lab assignment focuses on implementing the Jaccard Similarity Index to analyze user similarities based on shared friends in a social network. It includes tasks for calculating the index, parsing user data, and interpreting results to identify high-similarity user pairs. The implications of these findings include friendship recommendations, community detection, and insights into influence within social networks.

Uploaded by

lamya.gandhi4
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

CS342: Social Network Analysis

Lab Assignment - 6

Date Assigned: 11/03/2025 Date Submitted : 30/03/2025

Submitted By:
Name: Suchi Desai

Roll No: U22CS018


Branch: CSE
Semester: 06th Sem
Divison : A

Department of Computer Science and Engineering

SV NATIONAL INSTITUTE OF TECHNOLOGY SURAT


2025
Task 1) Implement the Jaccard Similarity Index to calculate the similarity between pairs of users based on
their shared friends.
The formula for Jaccard Similarity is: J(A,B)=∣A∩B∣/∣A∪B∣
Where:
 A and B represent the sets of friends for two users.
 A∩B is the set of common friends between both users.
 A∪B is the set of all unique friends of both users

Task 2) Load the dataset and parse the user and friendship information.
 Define a function to calculate the Jaccard Similarity Index between two users based on their friends.
 Compute the Jaccard Similarity for pairs of users in the network.

Task 3) Interpret the results of the Jaccard Similarity Index. Users with a higher similarity score share more
common friends.
 Identify pairs of users with high similarity and discuss potential implications, such as recommending
friendships or identifying closely connected communities.

Identifying High-Similarity User Pairs & Implications


After computing Jaccard Similarity for all user pairs in the Facebook friendship network, we identified 20 pairs
of users with high similarity scores (≥ 0.5). These users share a significant portion of their friends, indicating
strong social connections.
Implications:
1. Friendship Recommendations: Users with high similarity but not directly connected can be
recommended as potential friends. This can help expand social circles and foster new connections.
2. Community Detection: Groups of highly similar users can indicate tightly-knit communities or sub-
networks within the larger social graph. This insight can be used for targeted engagement, group
suggestions, or event recommendations.
3. Influence & Trust Networks: Users with a high number of shared friends may be more influential
within their social groups, making them key nodes in network analysis for marketing or content
sharing.
These findings can enhance social networking strategies, improve friend suggestions, and help in community
detection and analysis.

You might also like