IEICE Technical Committee Submission System
Conference Paper's Information		 Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2023-10-10 15:35
[Poster Presentation] An Evaluation of the Generalizability of Influencer Prediction Models between Social Networks in Different Domains
Kota Tahara, Sho Tsugawa (ITF)
Abstract (in Japanese) (See Japanese page) 
(in English) Identifying influencers on social media is one of the important research issues. Various methods for identifying influencers have been proposed, among which the use of machine learning has shown particular promise. However, most of the existing studies constructed an influencer prediction model for a given social graph and apply the model to the same graph. Therefore, the generalizability of the prediction model to graphs different from the training source has not been sufficiently clarified. In this paper, we aim to clarify how accurately influencers can be predicted when predicting influencers defined by real data of information diffusion and influencers defined by information diffusion models in cross-domain prediction settings. Specifically, we train models using Unsupervised Domain Adaptive Graph Convolutional Networks (UDA-GCN) on each of three social media datasets. We apply the constructed models to datasets different from the training source and evaluate their prediction accuracy. The results show that the prediction accuracy of the models exceed 80% of the prediction accuracy of the model constructed in the target domain.
Keyword (in Japanese) (See Japanese page) 
(in English) social graph / influencer / domain adaptation / graph neural network / information diffusion model / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee MIKA  
Conference Date 2023-10-10 - 2023-10-12 
Place (in Japanese) (See Japanese page) 
Place (in English) Okinawa Jichikaikan 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To MIKA 
Conference Code 2023-10-MIKA 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) An Evaluation of the Generalizability of Influencer Prediction Models between Social Networks in Different Domains 
Sub Title (in English)  
Keyword(1) social graph  
Keyword(2) influencer  
Keyword(3) domain adaptation  
Keyword(4) graph neural network  
Keyword(5) information diffusion model  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Kota Tahara  
1st Author's Affiliation University of Tsukuba (ITF)
2nd Author's Name Sho Tsugawa  
2nd Author's Affiliation University of Tsukuba (ITF)
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2023-10-10 15:35:00 
Presentation Time 90 minutes 
Registration for MIKA 
Paper #  
Volume (vol) vol. 
Number (no)  
Page  
#Pages  
Date of Issue  

[Return to Top Page]

[Return to IEICE Web Page]
The Institute of Electronics, Information and Communication Engineers (IEICE), Japan