Assignment 9: Social Network Analysis (30 Accounts Instagram)

SOCIAL NETWORK ANALYSIS

The 30 accounts Instagram are:
1. Narisha
2. Fifin
3. Sandi
4. Lathiefa
5. Eko
6. Ilham
7. Akbar
8. Biagi
9. Adit
10. Meta
11.Abdullah
12. Vhio
13. Anun
14. Ayta
15. Syifa
16. Ica
17. Niken
18. Firdha
19. Naomi
20. Adrian
21. Fauzi
22. Faza
23. Nadya P.
24. Karina
25. Arlinda
26. Sabrina
27. Andini
28. Melati
29. Calvin
30. Laudza

To describe this matrix, we use number 1 and 0. For example:

• Narisha is following Fifin. So, use number 1 to describe this relationship
• The same account cannot follow themselves. So, use number 0 to describe this relationship
• Narisha does not follow Adrian. So,  use number 0 to describe this relationship

This is the matrix of "following relationship" between 30 accounts Instagram:

from the matrix above, the plots is:

CLOSENESS

 

From the picture above, can conclude that the largest closeness value is ilham with a score of 0.9354839 because he followed 28 from 30 Instagram accounts and people also give followed back to Ilham.

BETWEENNESS

Betweenness can be assumed as a symbol of "strength"  or  "influence" of a node in social networks.  This is because the node is a bridge between one node to another node. So, from the picture above, can conclude that the largest betweenness score is Ilham with a score of  28.2577011.

KEY PLAYER

Based on this social network analysis, Ilham is the key player because he has the highest score of closeness and betweenness.

OUTDEGREE

INDEGREE

FREEMAN

Assignment 8 Big Data: Social Network Analysis

SNA
Social Network Analysis

What is Social Network Analysis?
Social network analysis (SNA) is the mapping and measuring of relationships and flows between people, groups, organizations, computers, URLs, and other connected information/knowledge entities.

SNA provides both a visual and a mathematical analysis of human relationships.

Potential of Social Network Analysis
a. In Inteligence = Social Network Analysis, as an analytic method, has inarguable applicability to the field of intelligence and is progressively reshaping the analytic landscape in terms of how analysts understand networks. For example, analysts currently use SNA to identify key people in an organization or social network, develop a strategic agent network, identify new agents and simulate information flows through a network. Beyond this, SNA can be easily combined with other analytic practices such as Geographic Information Systems (GIS), gravity model analysis or Intelligence Preparation of the Battlefield (IPB) to create robust, predictive analyses.

b. Tool for monitoring and evaluation of capacity building interventions
The project exploited existing monitoring and
evaluation data to: identify elements of AWARD’s interventions, strategies and theories of change
that intentionally (and unintentionally) facilitate networking; understand which factors within and outside of the fellowship (related to geographical proximity, social interactions, etc.) facilitate
networking; examine how networking is associated with empowerment outcomes; and to discuss how AWARD should measure network mechanisms and benefits better in the future.

Assignment 7 Big Data: Association Rules Ao

ASSOCIATION

Definition
Association rules are if/then statements that help uncover relationships between seemingly unrelated data in a relational database or another information repository.

Part of Association
An association rule has two parts, there is an antecedent (if) and a consequent (then).
a. An antecedent is an item found within the data.
b. A consequent is an item found in combination with the antecedent.

Uses of Association
In data mining, association rules are useful for analyzing and predicting customer behaviour. They play an important part in customer analytics, market basket analysis, product clustering, catalogue design and store layout.

Programmers use association rules to build programs capable of machine learning. Machine learning is a type of artificial intelligence (AI) that seeks to build programs with the ability to become more efficient without being explicitly programmed.

Example of Association
Association rule mining (ARM) algorithms are used to extract associations among a large set of items or events. This example analyzes the association of outcome of the match with opponent team e.g., Australia, Pakistan, Sri Lanka, type of venue (home ground, opponent ground or neutral venue), inning order (setting the target, chasing the target) and outcome of the toss.

This is Dataset 1 = All ODI matches played by team India till 05- June-2010.

The performance of team India against Australia is dismal. The toss outcome, innings order and venue do not have any impact on the performance of team India against Australia. This finding clearly shows the superiority of Australia over team India. Further, Australia is one of the top-ranked teams in world cricket for a long period of time.

Team India has performed well against England at home as well as away from home, except when team India bats first in both conditions, or wins toss in away conditions.

The performance of Team India against Pakistan is not encouraging at home and away conditions. The chance of Team India winning while chasing the target against Pakistan is 58% when playing away from home. Team India’s performance against South Africa is better in home condition than in away condition. India wins against South Africa at home but loses most of the time while playing away from home with a relatively high level of confidence.

The performance of team India is commendable against Sri Lanka. The toss outcome, innings order and venue have not impacted the performance of team India against. One of the interesting associations that came out of this study is the performance of the West Indies cricket team against team India. Team India’s chance of winning against West Indies is 72% when team India wins the toss and bats first, whereas other rules conclude that team India will lose against West Indies in all other conditions. 

This is Dataset 2 = ODI matched played by India during the last ten years (since 25-March-2001 to 05-June-2010). Dataset 2 is a subset of dataset 1.

Even in the last ten years, India’s performance has not improved against Australia. Team India has lost to Australia irrespective of playing conditions. A comparison between the two data sets shows that India’s chance of winning against Australia has dropped considerably over time; the confidence with which India loses has increased while the outcome does not depend on the pitch or innings order.

Against England, it is interesting to find the Team India’s record of chasing is more promising in away condition if Team India has lost the toss, whereas it is otherwise, even in the last ten years. In home conditions, if team India bats first, then the chance of team India losing the match against England is 86%.

Team India wins against Pakistan while playing away from home. Team India winning the toss matters at home as well as away from home.

The outcome of India vs. Sri Lanka matches has remained almost unchanged over time though confidence of both winning and losing increased.

In the last ten years, India has won more matches even while playing away from home than the overall scenario and the confidence of winning matches has also increased. In essence, India has adapted itself to the changing conditions outside the country, in the last ten years. Indian cricket team has won 102 matches out of 225 matches with a winning percentage of around 55%.