Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism

Elnaz Meydani; Christoph Düsing; Matthias Trier

doi:10.1007/978-3-030-86797-3_5

Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism

Elnaz Meydani^*, Christoph Düsing, Matthias Trier

^*Corresponding author for this work

Department of Digitalization

University of Paderborn

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Recommender Systems provide users with recommendations for potential items of interest in applications like e-commerce and social media. User information such as past item ratings and personal data can be considered as inputs of these systems. In this study, we aim to utilize a trust-graph-based Neural Network in the recommendation process. The proposed method tries to increase the performance of graph-based RSs by considering the inferred level of trust and its evolution. These recommendations will not only be based on the user information itself but will be fueled by information about associates in the network. To improve the system performance, we develop an attention mechanism to infer a level of trust for each connection in the network. As users are likely to be influenced more by those whom they trust the most, our method might lead to more personalized recommendations, which is likely to increase the user experience and satisfaction.

Original language	English
Title of host publication	Innovation Through Information Systems : Volume II: A Collection of Latest Research on Technology Issues
Editors	Frederik Ahlemann, Reinhard Schütte, Stefan Stieglitz
Number of pages	6
Place of Publication	Cham
Publisher	Springer
Publication date	2021
Pages	72-77
ISBN (Print)	9783030867966
ISBN (Electronic)	9783030867973
DOIs	https://doi.org/10.1007/978-3-030-86797-3_5
Publication status	Published - 2021
Event	16th International Conference on Wirtschaftsinformatik. WI 2021 - Virtual Conference, Germany Duration: 9 Mar 2021 → 11 Mar 2021 Conference number: 16 https://wi2021.de/start-2.html

Conference

Conference	16th International Conference on Wirtschaftsinformatik. WI 2021
Number	16
Location	Virtual Conference
Country/Territory	Germany
Period	09/03/2021 → 11/03/2021
Internet address	https://wi2021.de/start-2.html

Series	Lecture Notes in Information Systems and Organisation
Volume	47
ISSN	2195-4968

Keywords

Recommender systems
Trust-aware recommendations
Autoencoders
Attention mechanism

Access to Document

10.1007/978-3-030-86797-3_5Licence: Unspecified

Handle.net

Persistent link

Cite this

Meydani, E., Düsing, C., & Trier, M. (2021). Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism. In F. Ahlemann, R. Schütte, & S. Stieglitz (Eds.), Innovation Through Information Systems: Volume II: A Collection of Latest Research on Technology Issues (pp. 72-77). Springer. Lecture Notes in Information Systems and Organisation Vol. 47 https://doi.org/10.1007/978-3-030-86797-3_5

Meydani, Elnaz ; Düsing, Christoph ; Trier, Matthias. / Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism. Innovation Through Information Systems: Volume II: A Collection of Latest Research on Technology Issues. editor / Frederik Ahlemann ; Reinhard Schütte ; Stefan Stieglitz. Cham : Springer, 2021. pp. 72-77 (Lecture Notes in Information Systems and Organisation, Vol. 47).

@inproceedings{94c5d997ccac4786a2708a109cdc124b,

title = "Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism",

abstract = "Recommender Systems provide users with recommendations for potential items of interest in applications like e-commerce and social media. User information such as past item ratings and personal data can be considered as inputs of these systems. In this study, we aim to utilize a trust-graph-based Neural Network in the recommendation process. The proposed method tries to increase the performance of graph-based RSs by considering the inferred level of trust and its evolution. These recommendations will not only be based on the user information itself but will be fueled by information about associates in the network. To improve the system performance, we develop an attention mechanism to infer a level of trust for each connection in the network. As users are likely to be influenced more by those whom they trust the most, our method might lead to more personalized recommendations, which is likely to increase the user experience and satisfaction.",

keywords = "Recommender systems, Trust-aware recommendations, Autoencoders, Attention mechanism, Recommender systems, Trust-aware recommendations, Autoencoders, Attention mechanism",

author = "Elnaz Meydani and Christoph D{\"u}sing and Matthias Trier",

year = "2021",

doi = "10.1007/978-3-030-86797-3_5",

language = "English",

isbn = "9783030867966",

series = "Lecture Notes in Information Systems and Organisation",

publisher = "Springer",

pages = "72--77",

editor = "Frederik Ahlemann and Reinhard Sch{\"u}tte and Stefan Stieglitz",

booktitle = "Innovation Through Information Systems",

address = "Germany",

note = "null ; Conference date: 09-03-2021 Through 11-03-2021",

url = "https://wi2021.de/start-2.html",

}

Meydani, E, Düsing, C & Trier, M 2021, Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism. in F Ahlemann, R Schütte & S Stieglitz (eds), Innovation Through Information Systems: Volume II: A Collection of Latest Research on Technology Issues. Springer, Cham, Lecture Notes in Information Systems and Organisation, vol. 47, pp. 72-77, 16th International Conference on Wirtschaftsinformatik. WI 2021, North Rhine-Westphalia, Germany, 09/03/2021. https://doi.org/10.1007/978-3-030-86797-3_5

Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism. / Meydani, Elnaz; Düsing, Christoph; Trier, Matthias.

Innovation Through Information Systems: Volume II: A Collection of Latest Research on Technology Issues. ed. / Frederik Ahlemann; Reinhard Schütte; Stefan Stieglitz. Cham : Springer, 2021. p. 72-77 (Lecture Notes in Information Systems and Organisation, Vol. 47).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism

AU - Meydani, Elnaz

AU - Düsing, Christoph

AU - Trier, Matthias

N1 - Conference code: 16

PY - 2021

Y1 - 2021

N2 - Recommender Systems provide users with recommendations for potential items of interest in applications like e-commerce and social media. User information such as past item ratings and personal data can be considered as inputs of these systems. In this study, we aim to utilize a trust-graph-based Neural Network in the recommendation process. The proposed method tries to increase the performance of graph-based RSs by considering the inferred level of trust and its evolution. These recommendations will not only be based on the user information itself but will be fueled by information about associates in the network. To improve the system performance, we develop an attention mechanism to infer a level of trust for each connection in the network. As users are likely to be influenced more by those whom they trust the most, our method might lead to more personalized recommendations, which is likely to increase the user experience and satisfaction.

AB - Recommender Systems provide users with recommendations for potential items of interest in applications like e-commerce and social media. User information such as past item ratings and personal data can be considered as inputs of these systems. In this study, we aim to utilize a trust-graph-based Neural Network in the recommendation process. The proposed method tries to increase the performance of graph-based RSs by considering the inferred level of trust and its evolution. These recommendations will not only be based on the user information itself but will be fueled by information about associates in the network. To improve the system performance, we develop an attention mechanism to infer a level of trust for each connection in the network. As users are likely to be influenced more by those whom they trust the most, our method might lead to more personalized recommendations, which is likely to increase the user experience and satisfaction.

KW - Recommender systems

KW - Trust-aware recommendations

KW - Autoencoders

KW - Attention mechanism

KW - Recommender systems

KW - Trust-aware recommendations

KW - Autoencoders

KW - Attention mechanism

U2 - 10.1007/978-3-030-86797-3_5

DO - 10.1007/978-3-030-86797-3_5

M3 - Article in proceedings

SN - 9783030867966

T3 - Lecture Notes in Information Systems and Organisation

SP - 72

EP - 77

BT - Innovation Through Information Systems

A2 - Ahlemann, Frederik

A2 - Schütte, Reinhard

A2 - Stieglitz, Stefan

PB - Springer

CY - Cham

Y2 - 9 March 2021 through 11 March 2021

ER -

Meydani E, Düsing C, Trier M. Towards a Trust-aware Item Recommendation System on a Graph Autoencoder with Attention Mechanism. In Ahlemann F, Schütte R, Stieglitz S, editors, Innovation Through Information Systems: Volume II: A Collection of Latest Research on Technology Issues. Cham: Springer. 2021. p. 72-77. (Lecture Notes in Information Systems and Organisation, Vol. 47). doi: 10.1007/978-3-030-86797-3_5