Opinion mining from twitter data using evolutionary multinomial mixture models

TL;DR

This paper introduces an evolutionary clustering method using multinomial mixture models to automatically analyze and track the evolving public opinion images of political entities on Twitter over time.

Contribution

It presents a novel parametric link-based evolutionary clustering approach for multinomial mixture models, improving analysis of temporal opinion data from social media.

Findings

The method outperforms state-of-the-art clustering techniques.

It effectively captures the temporal evolution of opinion clusters.

Results demonstrate improved interpretability of opinion dynamics.

Abstract

Image of an entity can be defined as a structured and dynamic representation which can be extracted from the opinions of a group of users or population. Automatic extraction of such an image has certain importance in political science and sociology related studies, e.g., when an extended inquiry from large-scale data is required. We study the images of two politically significant entities of France. These images are constructed by analyzing the opinions collected from a well known social media called Twitter. Our goal is to build a system which can be used to automatically extract the image of entities over time. In this paper, we propose a novel evolutionary clustering method based on the parametric link among Multinomial mixture models. First we propose the formulation of a generalized model that establishes parametric links among the Multinomial distributions. Afterward, we follow a model-based clustering approach to explore different parametric sub-models and select the best model. For the experiments, first we use synthetic temporal data. Next, we apply the method to analyze the annotated social media data. Results show that the proposed method is better than the state-of-the-art based on the common evaluation metrics. Additionally, our method can provide interpretation about the temporal evolution of the clusters.