DURGESH716 / Fake-Instagram-Profile-Detection

Model Detects Fake Instagram Profiles using Deep Learning Approach of Artificial Neural Networks (ANN) for the fair use of social media

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

"Fake Instagram Profile Detction using ANN"

What is Instagram?

Instagram is an photo and video sharing social networking service founded in 2010 by Kevin Systrom and Mike Krieger, and later acquired by American company Facebook Inc. The app allows users to upload media that can be edited with filters and organized by hashtags and geographical tagging.

Problem Statement and Business Case:-

There are millions upon millions of Insta users out there, but organically engaging and attracting followers to your profile takes time. Time that a lot of businesses and entrepreneurs don’t have. Luckily, you can now gain hundreds to thousands of followers instantly - by purchasing them.

Stacking up your number of Instagram followers can instantly build your brand credit and get you noticed quick while building relationships and growing your Instagram account. There is also the fact that followers bring more followers! Some businesses benefit by purchasing a small amount of followers, resulting in a quick boost of social media presence.

Pre-Requisites / Technologies Used:-

  • Python Programming Language (Intermediate), Statistics, Probability and ANN (Artificial Neural Networks)
  • Libraries: NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn and tensorflow

Step_1: Dataset Cleaning and Data Exploration:-

  • Dealing with null values and missing values like is.na() to check them
  • Using functions to get familiar with data like info(), describe(), value_counts()
  • Visualizing data using graphs like histogram, count-plot, heatmap, displot, etc.

Step_2: Data Pre-Processing and Training the Model:-

  • Performing Scaling: A method used to scale the range of independent variables or features of data
  • Performing Normalization: The process of translating data into the range 0 to 1

Step_3: Measuring the performance of the model:-

  • Using Confusion Matrix: "Compares true value with predicted value"
  • Acheived Accuracy of 0.96 (96%) xand used different classification report.

Show 💗 by ⭐ My Repository

About

Model Detects Fake Instagram Profiles using Deep Learning Approach of Artificial Neural Networks (ANN) for the fair use of social media


Languages

Language:Python 100.0%