Research

Curiosity to predict personality, behavior, and need for this is not
as new as invent of social media. Personality prediction to better
accuracy could be very useful for society. There are many papers
and researches conducted on the usefulness of the data for various
purposes like in marketing, dating suggestions, organization
development, personalized recommendations and health care to
name a few.
With the introduction and extreme popularity of Online Social
Networking Sites like Facebook, Twitter and LinkedIn numerous
researches were conducted based on public data available, online
social networking applications and social behavior towards
friends and followers to predict the personality. Structured mining
of the social media content can provide us the ability to predict
some personality traits. This survey aims at providing researchers
with an overview of various strategies used for studies and
research concentrating on predicting user personality and behavior
using online social networking site content. Their positives,
limitations are well summarized as reported in the literature.
Finally, a brief discussion including open issues for further
research in the area of social networking site based personality
prediction preceding conclusion.

Interests

  • Data Science
  • Predictive Modeling
  • Business Intelligence
  • Machine Learning
  • Big Data, HDFS Eco system, SPARK
  • Data Integration and Data warehouse
  • Expert Level

Research Projects

  • Personality Predection

    Analyzing social media data to predict personality of the user

    Personality prediction and its applications have been widely studied in various fields including psychology and social media. The emergence of online social networks provides novel opportunities to obtain information about user behaviors and demographics, and to study such social and psychological phenomena in a data-driven manner. This thesis attempts to address two different but related research questions:
    1) can we predict a user’s personality from their demographic information (in social media) such as date     of birth (DOB) and gender, and
    2) does personality play any role in persuasion?

    To answer the first research question, we use the Cambridge University data set consisting of data of 228,343 users. The data was collected using a personality survey app on Facebook. For the second research question, the MIT Media Lab dataset consisting of 130 participants is used. This dataset was captured using an Android-based mobile phone application which was specially designed to collect behavioral and passive information such as Bluetooth, SMS log, GPS location and accelerometer sensors. Our statistical analyses suggest that: (1) there are certain personality traits which relate to DOB, making DOB a very quick indicator of one’s personality where there exists a relationship, and (2) personality plays an important role in choosing the appropriate persuasion mechanism. We believe that our findings can have implications in healthcare, civic society, marketing, and education.

  • Persuasive Recommendation System

    The Role of Personality in Persuasion

    We propose and examine five research questions to understand the role of personality in social persuasion for behavior change:

    RESEARCH QUESTION 1

    Does the same intervention work for all kind of people?

    RESEARCH QUESTION 2

    Is behavior change a function of my personality and reward offered to me?

    RESEARCH QUESTION 3

    Is behavior change a function of personalities of my peers after controlling the reward which I get?

    RESEARCH QUESTION 4

    Is behavior change a function of the similarity between me and my peers’ personalities?

    RESEARCH QUESTION 5

    Is the difference between short-term and long-term behavior change a function of my personality after controlling the reward which I get?