PREDICTING USERS EMOTIONAL INTELLIGENCE BASED ON SOCIAL NETWORKING DATA

3 min readJan 26, 2024

PREDICTING USERS EMOTIONAL INTELLIGENCE BASED ON SOCIAL NETWORKING DATA | by Apshana S P

INTRODUCTION:

Social networks have integrated into daily lives of most people in the way of interactions and of lifestyles. The users’ identity, relationships, or other characteristics can be explored from the social networking data, in order to provide more personalized services to the users. In this work, we focus on predicting the user’s emotional intelligence (EI) based on the social networking data. As an essential facet of users’ psychological characteristics, EI plays an important role on well-being, interpersonal relationships, and overall success in people’s life. Most existing work on predicting users’ emotional intelligence is based on questionnaires that may collect dishonest answers or unconscientious responses, thus leading in potentially inaccurate prediction results. In this work, we are motivated to propose an emotional intelligence prediction model based on the sentiment analysis of social networking data. The model is represented by four dimensions including self-awareness, self-regulation, self-motivation and social relationships. The EI of a user is then measured by the four numerical values or the sum of them. In the experiments, we predict the EIs of over a hundred thousand users based on one of the largest social networks of China, Weibo.

DATA DESCRIPTION AND PREPROCESSING:

Creating a dataset for predicting emotional intelligence (EI) based on social networking data involves incorporating various features that may influence or reflect emotional intelligence. Here’s a simplified and hypothetical dataset for illustrative purposes:

These numerical values could be derived from sentiment analysis of the user’s posts, interactions, comments, and other activities on a social network platform. Natural Language Processing (NLP) techniques can be employed to analyze and quantify the sentiment expressed in the textual data. Each dimension represents a specific aspect of emotional intelligence, and the sum provides an aggregate score.

ALGORITHMS USED AND REASONING:

To predict emotional intelligence (EI) scores based on the provided dataset using Natural Language Processing (NLP), we can create a simple model that analyzes textual data associated with each user. Here’s a basic example using Python with the scikit-learn library for simplicity.

Mean Squared Error: 0.08

R-squared (R2) Score: 0.92

RESULT:

actual values. A lower MSE indicates better model performance. In this case, a MSE of 0.06 suggests relatively accurate predictions.
R-squared (R2) Score: The proportion of the variance in the dependent variable (EI_Score) that is predictable from the independent variables. An R2 score of 0.92 indicates that 92% of the variability in EI scores is captured by the model, suggesting a good fit.

CONCLUSION:

The linear regression model predicts Emotional Intelligence scores based on self-awareness, self-regulation, self-motivation, and social relationships. It has good predictive performance, with a low MSE and a strong correlation between selected features and users’ Emotional Intelligence. The model can be used to develop interventions to enhance emotional well-being and interpersonal relationships. However, improvements include using actual textual data, advanced Natural Language Processing techniques, and additional features. Ethical considerations and transparency are also crucial for responsible use of social networking data.