Project title

Personality & Gender Prediction From Twitter & Real-Time Images

Submitted to:

  • Dr. Vipul Mishra (Asst Professor Bennett University)
  • Divya Acharya (Ph.D. Scholar Bennett University)

Submitted By:

  1. Akshay Dashottar (ABES Engineering College)
  2. R. Meena (Mahendra Engineering College)
  3. Vineetha.V (Saintgits College of Engineering)

Project Description

Social media is a place where users present themselves to the world, revealing personal details and insights into their lives. Psychology researchers have worked to understand personality in a systematic way. Goal of this project is to develop learning models that can automatically Predict Person’s Personality. In this project MBTI, 16 Personality Traits are considered to analyse the twitter account of the person. This also includes a module which performs gender prediction wherein the visual image of a person predicts the gender of the person by taking images from gallery and at real time by webcam too. This project was developed using deep-convolutional neural networks(CNN) and Machine learning approach i.e., Support Vector Machine Classifier. To achieve this goal Google image dataset and MBTI dataset provided by Kaggle is used. The accuracy level at 100 epochs reached 98.71% for gender prediction and for twitter-based personality prediction it is 98%. The ultimate scope of Personality prediction is that it can be used in Psychology, HCI, Detection of mental illness, Human resource management, Interest prediction for predicting personality which can help in making life better for humans.

Project Poster

Get Latest Notification about

Please ignore if you have already signed up.

Announcements, news and innovations!

From in your inbox.

By submitting this form, you are consenting to receive marketing emails from: Bennett University. You can revoke your consent to receive emails at any time by using the SafeUnsubscribe® link, found at the bottom of every email.