A novel interest drift sensitivity academic paper recommender based on implicit feedback

Academic recommendation systems have been rapidly developed in recent years, helping researchers to find favorite paper. However, traditional methods applied to paper recommendation face more challenges. First, users can only read a small number of papers, resulting in a very sparse user-paper matri...

Full description

Saved in:
Bibliographic Details
Main Authors: Weiming Huang, Baisong Liu, Zhaoliang Wang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Egyptian Informatics Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110866524001014
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122195118456832
author Weiming Huang
Baisong Liu
Zhaoliang Wang
author_facet Weiming Huang
Baisong Liu
Zhaoliang Wang
author_sort Weiming Huang
collection DOAJ
description Academic recommendation systems have been rapidly developed in recent years, helping researchers to find favorite paper. However, traditional methods applied to paper recommendation face more challenges. First, users can only read a small number of papers, resulting in a very sparse user-paper matrix, but the method based on random sampling of negative samples is ineffective due to the uncertainty of negative samples. And users’ academic interests shift frequently, so the approach that ignores temporal information is not applicable. To overcome the above challenges, this paper proposes an implicit feedback-based interest drift-aware academic paper recommendation algorithm. The algorithm explicitly integrates the user’s interest drift into the model through regularization. The algorithm alleviates sparsity by introducing contextual information through a multiplicative law and significantly reduces the computational complexity by using a caching approach. Experimental results on two real paper recommendation datasets show that the proposed method outperforms current methods in terms of recommendation accuracy and computational efficiency.
format Article
id doaj-art-9ee69e7ddd6c4e7eac91651d609b7a9b
institution Kabale University
issn 1110-8665
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Egyptian Informatics Journal
spelling doaj-art-9ee69e7ddd6c4e7eac91651d609b7a9b2024-12-15T06:14:45ZengElsevierEgyptian Informatics Journal1110-86652024-12-0128100538A novel interest drift sensitivity academic paper recommender based on implicit feedbackWeiming Huang0Baisong Liu1Zhaoliang Wang2Ningbo University, Fenghua Street, Ningbo, 315211, Zhejiang Province, China; Inner Mongolia Metal Material Research Institute, Qingshan Street, Baotou, 014000, Inner Mongolia Province, ChinaNingbo University, Fenghua Street, Ningbo, 315211, Zhejiang Province, China; Corresponding author.Ningbo University, Fenghua Street, Ningbo, 315211, Zhejiang Province, ChinaAcademic recommendation systems have been rapidly developed in recent years, helping researchers to find favorite paper. However, traditional methods applied to paper recommendation face more challenges. First, users can only read a small number of papers, resulting in a very sparse user-paper matrix, but the method based on random sampling of negative samples is ineffective due to the uncertainty of negative samples. And users’ academic interests shift frequently, so the approach that ignores temporal information is not applicable. To overcome the above challenges, this paper proposes an implicit feedback-based interest drift-aware academic paper recommendation algorithm. The algorithm explicitly integrates the user’s interest drift into the model through regularization. The algorithm alleviates sparsity by introducing contextual information through a multiplicative law and significantly reduces the computational complexity by using a caching approach. Experimental results on two real paper recommendation datasets show that the proposed method outperforms current methods in terms of recommendation accuracy and computational efficiency.http://www.sciencedirect.com/science/article/pii/S1110866524001014Citation networkImplicit feedbackTopic modelInterest driftComputational complexity
spellingShingle Weiming Huang
Baisong Liu
Zhaoliang Wang
A novel interest drift sensitivity academic paper recommender based on implicit feedback
Egyptian Informatics Journal
Citation network
Implicit feedback
Topic model
Interest drift
Computational complexity
title A novel interest drift sensitivity academic paper recommender based on implicit feedback
title_full A novel interest drift sensitivity academic paper recommender based on implicit feedback
title_fullStr A novel interest drift sensitivity academic paper recommender based on implicit feedback
title_full_unstemmed A novel interest drift sensitivity academic paper recommender based on implicit feedback
title_short A novel interest drift sensitivity academic paper recommender based on implicit feedback
title_sort novel interest drift sensitivity academic paper recommender based on implicit feedback
topic Citation network
Implicit feedback
Topic model
Interest drift
Computational complexity
url http://www.sciencedirect.com/science/article/pii/S1110866524001014
work_keys_str_mv AT weiminghuang anovelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback
AT baisongliu anovelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback
AT zhaoliangwang anovelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback
AT weiminghuang novelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback
AT baisongliu novelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback
AT zhaoliangwang novelinterestdriftsensitivityacademicpaperrecommenderbasedonimplicitfeedback