Computational Models for Attitude and Actions Prediction

TL;DR

This paper introduces computational models that predict Twitter users' attitudes towards brands and their potential actions, validated through real-world datasets and integrated with visual analytics for customer engagement.

Contribution

It presents a novel framework combining attitude and action prediction models with empirical validation and integration into a visual analytics system.

Findings

Models accurately predict user attitudes and actions

Validation on real-world datasets confirms effectiveness

Framework supports customer intervention strategies

Abstract

In this paper, we present computational models to predict Twitter users' attitude towards a specific brand through their personal and social characteristics. We also predict their likelihood to take different actions based on their attitudes. In order to operationalize our research on users' attitude and actions, we collected ground-truth data through surveys of Twitter users. We have conducted experiments using two real world datasets to validate the effectiveness of our attitude and action prediction framework. Finally, we show how our models can be integrated with a visual analytics system for customer intervention.