Predicting opinion evolution based on information diffusion in social networks using a hybrid fuzzy based approach

Area of Science:

• Social Media Analysis
• Computational Social Science
• Information Science

Background:

• Social media is crucial for information dissemination and opinion analysis.
• Existing research often treats information diffusion and opinion analysis as separate fields.
• A unified approach is needed to understand the interplay between information spread and evolving public sentiment.

Purpose of the Study:

• To propose a novel framework for analyzing both information diffusion and opinion evolution on social media.
• To develop a predictive model for information spread and opinion dynamics.
• To address the limitations of separate analyses of information diffusion and opinion analysis.

Main Methods:

• Utilized a forest fire algorithm to identify information diffusers and non-diffusers in social networks.
• Employed fuzzy c-means clustering combined with the cuckoo search optimization algorithm.
• Clustered Twitter content to categorize opinions and track opinion changes over time.

Main Results:

• The proposed model demonstrated superior performance compared to existing methods.
• Achieved higher precision, recall, and accuracy in analyzing social media data.
• Successfully integrated information diffusion and opinion evolution analysis.

Conclusions:

• The novel framework effectively analyzes both information diffusion and opinion evolution simultaneously.
• The integrated approach offers improved predictive capabilities for social media dynamics.
• This research provides a significant advancement in understanding complex social media phenomena.