Saved in:
Bibliographic Details
Main Authors: Church, Kenneth, Alonso, Omar, Vickers, Peter, Sun, Jiameng, Ebrahimi, Abteen, Chandrasekar, Raman
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.05836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916315797651456
author Church, Kenneth
Alonso, Omar
Vickers, Peter
Sun, Jiameng
Ebrahimi, Abteen
Chandrasekar, Raman
author_facet Church, Kenneth
Alonso, Omar
Vickers, Peter
Sun, Jiameng
Ebrahimi, Abteen
Chandrasekar, Raman
contents We argue that Content-based filtering (CBF) and Graph-based methods (GB) complement one another in Academic Search recommendations. The scientific literature can be viewed as a conversation between authors and the audience. CBF uses abstracts to infer authors' positions, and GB uses citations to infer responses from the audience. In this paper, we describe nine differences between CBF and GB, as well as synergistic opportunities for hybrid combinations. Two embeddings will be used to illustrate these opportunities: (1) Specter, a CBF method based on BERT-like deepnet encodings of abstracts, and (2) ProNE, a GB method based on spectral clustering of more than 200M papers and 2B citations from Semantic Scholar.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05836
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Academic Article Recommendation Using Multiple Perspectives
Church, Kenneth
Alonso, Omar
Vickers, Peter
Sun, Jiameng
Ebrahimi, Abteen
Chandrasekar, Raman
Information Retrieval
We argue that Content-based filtering (CBF) and Graph-based methods (GB) complement one another in Academic Search recommendations. The scientific literature can be viewed as a conversation between authors and the audience. CBF uses abstracts to infer authors' positions, and GB uses citations to infer responses from the audience. In this paper, we describe nine differences between CBF and GB, as well as synergistic opportunities for hybrid combinations. Two embeddings will be used to illustrate these opportunities: (1) Specter, a CBF method based on BERT-like deepnet encodings of abstracts, and (2) ProNE, a GB method based on spectral clustering of more than 200M papers and 2B citations from Semantic Scholar.
title Academic Article Recommendation Using Multiple Perspectives
topic Information Retrieval
url https://arxiv.org/abs/2407.05836