TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction

Abstract According to historical retweet relationships that reveal public attention, information popularity prediction aims to forecast the incremental size of the given information cascades. Existing work independently models user dynamic preference with discrete cascade snapshots technology, they...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanchao Liu, Junpeng Gong, Wenchao Song, Chi Zhang, Pengzhou Zhang
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00170-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225842482216960
author Yanchao Liu
Junpeng Gong
Wenchao Song
Chi Zhang
Pengzhou Zhang
author_facet Yanchao Liu
Junpeng Gong
Wenchao Song
Chi Zhang
Pengzhou Zhang
author_sort Yanchao Liu
collection DOAJ
description Abstract According to historical retweet relationships that reveal public attention, information popularity prediction aims to forecast the incremental size of the given information cascades. Existing work independently models user dynamic preference with discrete cascade snapshots technology, they ignore the global structure of information cascades and inefficient tendency semantic representation, leading to suboptimal performance. To overcome the those issues, we introduce a novel Tendency-Enhanced Evolution Graph KAN Transformer framework ( TEGKT ), which is specifically tailored for information popularity prediction. To enhance the ability to express tendency semantics, we construct a tendency encoding learning module, which can effectively exhume the potential high-level dependency relationship among tendency semantics. To capture the global structure of cascade snapshots during the observation period, we design the evolution Graph KAN Transformer architecture to improve the expressive ability of information cascade representation, and its weighted parameter is optimized by gated recurrent units (GRU). Bi-directional gate recurrent units (Bi-GRU) are used to explore the dynamic evolution between cascade snapshots. Extensive experiments conducted on three public datasets show that the proposed model significantly outperforms the advanced methods, which achieves by 3.34% and 4.09% on the Weibo 0.5h dataset in terms of MSLE and MAPE evaluation metrics, respectively, validating its effectiveness. The research provides a better understanding of the laws of information diffusion.
format Article
id doaj-art-6f2e8852708e4051a975e2be294e7aeb
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-6f2e8852708e4051a975e2be294e7aeb2025-08-24T11:53:23ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137711610.1007/s44443-025-00170-8TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity predictionYanchao Liu0Junpeng Gong1Wenchao Song2Chi Zhang3Pengzhou Zhang4Communication University of ChinaCommunication University of ChinaCommunication University of ChinaCommunication University of ChinaCommunication University of ChinaAbstract According to historical retweet relationships that reveal public attention, information popularity prediction aims to forecast the incremental size of the given information cascades. Existing work independently models user dynamic preference with discrete cascade snapshots technology, they ignore the global structure of information cascades and inefficient tendency semantic representation, leading to suboptimal performance. To overcome the those issues, we introduce a novel Tendency-Enhanced Evolution Graph KAN Transformer framework ( TEGKT ), which is specifically tailored for information popularity prediction. To enhance the ability to express tendency semantics, we construct a tendency encoding learning module, which can effectively exhume the potential high-level dependency relationship among tendency semantics. To capture the global structure of cascade snapshots during the observation period, we design the evolution Graph KAN Transformer architecture to improve the expressive ability of information cascade representation, and its weighted parameter is optimized by gated recurrent units (GRU). Bi-directional gate recurrent units (Bi-GRU) are used to explore the dynamic evolution between cascade snapshots. Extensive experiments conducted on three public datasets show that the proposed model significantly outperforms the advanced methods, which achieves by 3.34% and 4.09% on the Weibo 0.5h dataset in terms of MSLE and MAPE evaluation metrics, respectively, validating its effectiveness. The research provides a better understanding of the laws of information diffusion.https://doi.org/10.1007/s44443-025-00170-8Information popularity predictionEvolution graph KAN transformerTendency semantic
spellingShingle Yanchao Liu
Junpeng Gong
Wenchao Song
Chi Zhang
Pengzhou Zhang
TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
Journal of King Saud University: Computer and Information Sciences
Information popularity prediction
Evolution graph KAN transformer
Tendency semantic
title TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
title_full TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
title_fullStr TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
title_full_unstemmed TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
title_short TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction
title_sort tegkt tendency enhanced evolution graph kan transformer for information popularity prediction
topic Information popularity prediction
Evolution graph KAN transformer
Tendency semantic
url https://doi.org/10.1007/s44443-025-00170-8
work_keys_str_mv AT yanchaoliu tegkttendencyenhancedevolutiongraphkantransformerforinformationpopularityprediction
AT junpenggong tegkttendencyenhancedevolutiongraphkantransformerforinformationpopularityprediction
AT wenchaosong tegkttendencyenhancedevolutiongraphkantransformerforinformationpopularityprediction
AT chizhang tegkttendencyenhancedevolutiongraphkantransformerforinformationpopularityprediction
AT pengzhouzhang tegkttendencyenhancedevolutiongraphkantransformerforinformationpopularityprediction