Towards explainability of hashtags in the light of Graph Spectral Clustering methods

Authors

  • Bartłomiej Starosta Institute of Computer Science of Polish Academy of Sciences
  • Mieczysław A. Kłopotek Institute of Computer Science of Polish Academy of Sciences
  • Sławomir T. Wierzchoń Institute of Computer Science of Polish Academy of Sciences

DOI:

https://doi.org/10.34739/si.2023.29.04

Keywords:

Graph Spectral Analysis, hashtag similarity, eigenvalue spectrograms, Explainable Artificial Intelligence

Abstract

Hashtags constitute an indispensable part of modern social media world. As more and more hashtags are invented, it becomes a necessity to create clusters of these hashtags. Nowadays, however, the clustering alone does not help the users. They are asking for justification or expressed in the modern AI language, the clustering has to be explainable. We discuss a novel approach to hashtag explanation via a measure of similarity between hashtags based on the Graph Spectral Analysis. The application of this similarity measure may go far beyond the classical clustering task. It can be used to provide with explanations for the hashtags. In this paper we propose such a novel view of the proposed hashtag similarity measure.

Downloads

Download data is not yet available.

Downloads

Published

26.12.2023

How to Cite

Starosta, B., Kłopotek, M. A., & Wierzchoń, S. T. (2023). Towards explainability of hashtags in the light of Graph Spectral Clustering methods. Studia Informatica. System and Information Technology, 29(2), 57-68. https://doi.org/10.34739/si.2023.29.04