EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Attentive Multi-Modal Topic Modeling for Richer Contextual Analysis of Text and Auxiliary Data

Hemadharsana Sakkaraja, Mahalakshmi Guruvayur Suryanarayanan, Sendhilkumar Selvaradjou

Applied Sciences · 20.11.2026 · 16 (22) · 11501

DOI: 10.3390/app162211501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 20.11.2026. Verfasst von Hemadharsana Sakkaraja und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Topic modeling has traditionally relied on textual data to uncover hidden themes within a corpus. However, with the increasing prevalence of multi-modal content in research and applications, there is a need to extend topic modeling to incorporate auxiliary modalities such as images, audio, and metadata. The paper introduces Multi-Modal Generative Topic Modeling with Cross-Attentive Networks (MM-GTM-CAN), a framework that uses a cross-attentive neural network to fuse embeddings from multiple modalities. Textual data is processed using a transformer-based encoder, while auxiliary data is encoded using modality-specific architectures. The fused embeddings are then passed through a Conditional Variational Autoencoder (CVAE) to generate contextually rich topics. We assessed topic models on a dataset of 6743 BMC Bioinformatics articles (2005–2015), in an 80:20 split, using a shared vocabulary and three random seeds. Latent Dirichlet Allocation (LDA) with five topics obtained a C_V coherence score of 0.560 ± 0.028, an NPMI score of 0.065 ± 0.013, a topic diversity score of 0.953 ± 0.023, and a held-out perplexity score of 351.7 ± 3.0. LDA with twenty topics achieved stronger coherence (C_V: 0.663) but lower diversity (0.847). Thus, the number of subjects is a trade-off between coherence and repetition. Overall, the suggested system increases topic coherence and allows for broader contextual analysis than prior modal techniques.

Zitieren

APA

Sakkaraja, H., Suryanarayanan, M. G., & Selvaradjou, S. (2026). Cross-Attentive Multi-Modal Topic Modeling for Richer Contextual Analysis of Text and Auxiliary Data. Applied Sciences, 16(22), 11501. https://doi.org/10.3390/app162211501

Vancouver

Sakkaraja H, Suryanarayanan MG, Selvaradjou S. Cross-Attentive Multi-Modal Topic Modeling for Richer Contextual Analysis of Text and Auxiliary Data. Applied Sciences. 2026;16(22):11501. doi:10.3390/app162211501

BibTeX
@article{Sakkaraja2026,
  author = {Sakkaraja, Hemadharsana and Suryanarayanan, Mahalakshmi Guruvayur and Selvaradjou, Sendhilkumar},
  title = {Cross-Attentive Multi-Modal Topic Modeling for Richer Contextual Analysis of Text and Auxiliary Data},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11501},
  doi = {10.3390/app162211501}
}
Kostenlos starten →