click here to download project abstract
–
V
ABSTRACT
At present social network sites are part of the life for most of the people.
Every day several people are creating their profiles on the social network platforms
and they are interacting with others independent of the user’s location and time. The
social network sites not only providing advantages to the users and also provide
security issues to the users as well their information. Spam Messages. Malicious
comments, Cyber bullying activities are very much common in today’s generation. All
these challenging activities are carried out in social platforms with the use of fake
profiles, this has imposed numerous challenges to our privacy policies. To analyze
who are encouraging threats in social network we need to classify the social
networks profiles of the users. In this project, we shall provide a new method that is
highly proficient in revealing fake account profiles in social media. We are proposing
a machine learning classification model that helps us classify users into genuine
users and bot accounts. Therefore, this project report highlights the review of Fake
Profile Detection on Social Networking Services by using Machine Learning.
VI
TABLE OF CONTENT
CHAPTER
NO
TITLE
PAGE
NO
ABSTRACT
V
LIST OF FIGURES
IX
LIST OF ABBREVIATION
X
1.
INTRODUCTION
1
1.1 MOTIVATION
1
1.2 MODEL IDLE
2
1.3 OBJECTIVES
2
1.4 OVERVIEW OF THE PROJECT
2
2.
LITERATURE SURVEY
4
3.
SCOPE AND REQUIREMENT ANALYSIS OF
PRESENT INVESTIGATION
7
3.1 EXISTING SYSTEM
7
3.2 PROPOSED SYSTEM
7
3.3 TECHNOLOGY USED
7
3.4 REQUIREMENT ANALYSIS
8
3.4.1 HARDWARE.ENVIRONMENT
8
3.4.2 SOFTWARE ENVIRONMENT
8
4.
METHODOLOGY AND ALGORITHMS USED
10
4.1 INTRODUCTION TO MACHINE LEARNING
10
4.2 TRAINING THE DATA
11
4.2.1 SUPERVISED LEARNING
11
VII
4.2.2 UNSUPERVISED LEARNING
11
4.3 METHODS IN SUPERVISED LEARNING
12
4.3.1 CLASSIFICATION
12
4.3.2 REGRESSION
13
4.4 APPROACHES IN CLASSIFICATION
13
4.4.1 DECISION TREE
14
4.4.2 XGBOOSTING ALGORITHM
15
4.5 SYSTEM ARCHITECTURE
16
4.6 IMPLEMENTATION OF ARCHITECTURE
19
4.6.1 DATASET & MODEL FEATURES
19
4.6.2 CORRELATIONS & DISTRIBUTION
PLOTS
20
4.6.3 MODEL EVALUATION & SCORING
24
4.6.4 TRAIN THE MODEL
24
5.
RESULTS AND DISCUSSION
25
5.1 RESULT
25
5.1.1 PRE-MODEL DATA VISUALISATION
25
5.1.2 MODEL INFORMATION
VISUALISATION
29
5.1.3
POST-MODEL
DATA
VISUALIZATION
33
6.
CONCLUSION AND FUTURE WORK
35
6.1 CONCLUSION
6.2 FUTURE WORK
REFERENCES
36
APPENDIX
39
