Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)

<Previous Article In Volume
Next Article In Volume>

Cross-Modal Approach to Clustering Multimodal Influencer Posts Using Healnet, Hdbscan and Topic Modelling

Authors
Hailey Maree Jaranilla1, *, Ian Joseph Sobrecaray1, *, Christian Maderazo1
1Department of Computer Information Science and Mathematics, School of Arts and Sciences, University of San Carlos, Cebu, Philippines
*Corresponding author. Email: hailey.jaranilla@gmail.com
*Corresponding author. Email: ian.sobrecaray@gmail.com
Corresponding Authors
Hailey Maree Jaranilla, Ian Joseph Sobrecaray
Available Online 6 April 2026.
DOI
10.2991/978-94-6239-624-1_11How to use a DOI?
Keywords
Machine Learning and Data Analytics; Social Media Marketing; Influencer Posts and Media
Abstract

Social media influencers play a huge role when it comes to a business’ marketing and PR strategy. However, with the large variety and volume of influencers and posts, it can be difficult for businesses to identify content themes and audience interest in social media posts, making it difficult for them to position their brand campaigns better in the industry. Clustering, a data science approach used to reveal distinct groupings on data based on similar internal group characteristics, can identify dominant themes within social media posts. This paper proposed a cross-modal approach for the clustering of multimodal influencers posts by incorporating HEALNet for multimodal fusion, HDBSCAN for clustering and topic modelling using BERTopic’s c-TF-IDF for getting the topic labels of clusters. The results showed that the clusters generated were locally coherent and well separated, and the fusion model effectively captured cross-modal relationships that produced meaningful and internally consistent groups of topics.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
Series
Advances in Economics, Business and Management Research
Publication Date
6 April 2026
ISBN
978-94-6239-624-1
ISSN
2352-5428
DOI
10.2991/978-94-6239-624-1_11How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Hailey Maree Jaranilla
AU  - Ian Joseph Sobrecaray
AU  - Christian Maderazo
PY  - 2026
DA  - 2026/04/06
TI  - Cross-Modal Approach to Clustering Multimodal Influencer Posts Using Healnet, Hdbscan and Topic Modelling
BT  - Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
PB  - Atlantis Press
SP  - 142
EP  - 153
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-624-1_11
DO  - 10.2991/978-94-6239-624-1_11
ID  - Jaranilla2026
ER  -