Local Is Good: A Fast Citation Recommendation Approach

@inproceedings{Jia2018LocalIG,
  title={Local Is Good: A Fast Citation Recommendation Approach},
  author={Haofeng Jia and Erik Saule},
  booktitle={ECIR},
  year={2018}
}
Finding relevant research works from the large number of published articles has become a nontrivial problem. In this paper, we consider the problem of citation recommendation where the query is a set of seed papers. Collaborative filtering and PaperRank are classical approaches for this task. Previous work has shown PaperRank achieves better recommendation in experiments. However, the running time of PaperRank typically depends on the size of input graph and thus tends to be expensive. Here we… 
Towards Finding Non-obvious Papers: An Analysis of Citation Recommender Systems
TLDR
This paper considers the problem of citation recommendation by extending a set of known-to-be-relevant references and proposes to combine author, venue and keyword information to interpret the citation behavior behind loosely connected papers.
Citation Recommendations Considering Content and Structural Context Embedding
  • Yang Zhang, Qiang Ma
  • Computer Science
    2020 IEEE International Conference on Big Data and Smart Computing (BigComp)
  • 2020
TLDR
A novel embedding algorithm DocCit2Vec is proposed, along with the new concept of "structural context", to tackle the aforementioned issues.
DocCit2Vec: Citation Recommendation via Embedding of Content and Structural Contexts
TLDR
This study proposes a novel embedding algorithm, namely DocCit2Vec, along with the new concept of “structural context”, to address the aforementioned issues of citation recommendation and classification tasks.
SVD-CNN: A Convolutional Neural Network Model with Orthogonal Constraints Based on SVD for Context-Aware Citation Recommendation
TLDR
A novel context-aware citation recommendation approach that can essentially improve the orthogonality of the weight matrix and explore more accurate citation patterns is proposed and quantitatively shows that the various reference patterns in the paper have interactional features that can significantly affect link prediction.
Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet
TLDR
A novel scientific paper modelling for citation recommendations, namely Multi-Positive BERT Model for Citation Recommendation (MP-BERT4CR), complied with a series of Multi- Positive Triplet objectives to recommend multiple positive citations for a query context.
Dual Attention Model for Citation Recommendation with Analyses on Explainability of Attention Mechanisms and Qualitative Experiments
TLDR
This study proposes a novel embedding-based neural network called “dual attention model for citation recommendation (DACR)” to recommend citations during manuscript preparation that could find necessary citations which were not noticed by the authors in the past due to the limitations of the keyword-based searching.
Analisis sitasi publikasi tentang repositori bidang studi perpustakaan pada Web of Science selama pandemi
Introduction. Library repositories are indispensable for academics during a pandemic. This study aims to analyze citation trends during a pandemic.Methodology. This study uses bibliometric methods to
Citation recommendation: approaches and datasets
TLDR
This article presents an overview of the approaches and data sets for citation recommendation and identifies differences and commonalities using various dimensions, and sheds light on the evaluation methods and outline general challenges in the evaluation and how to meet them.
Dual Attention Model for Citation Recommendation
TLDR
This study proposes a novel embedding-based neural network called “dual attention model for citation recommendation (DACR)” to recommend citations during manuscript preparation that adapts embedding of three semantic information: words in the local context, structural contexts, and the section on which a user is working.

References

SHOWING 1-10 OF 14 REFERENCES
An Analysis of Citation Recommender Systems: Beyond the Obvious
TLDR
This paper considers the problem of citation recommendation by extending a set of known-to-be-relevant references and proposes to combine author, venue and keyword information to interpret the citation behavior behind loosely connected papers.
Fast Recommendation on Bibliographic Networks
TLDR
This paper proposes an efficient implementation of a sparse-matrix computation which arises in the authors' publicly available citation recommendation service called the advisor, and proposes techniques for storing the matrix in memory efficiently and reducing the number of cache misses.
Research Paper Recommender Systems: A Random-Walk Based Approach
  • M. Gori, A. Pucci
  • Computer Science
    2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06)
  • 2006
TLDR
This paper proposes a research paper recommending algorithm based on the citation graph and random-walker properties that is able to assign a preference score to a set of documents contained in a digital library and linked one each other by bibliographic references.
Can't see the forest for the trees?: a citation recommendation system
TLDR
This paper addresses the problem of citation recommendation using a singular value decomposition approach and shows that the proposed approach achieves significant success when compared with collaborative filtering methods on the citation recommendation task.
Beyond keyword search: discovering relevant scientific literature
TLDR
In a user study, researchers found the papers recommended by the method to be more useful, trustworthy and diverse than those selected by popular alternatives, such as Google Scholar and a state-of-the-art topic modeling approach.
On the recommending of citations for research papers
TLDR
This paper investigated six algorithms for selecting citations, evaluating them through offline experiments and an online experiment to gauge user opinion of the effectiveness of the algorithms and of the utility of such recommendations for common research tasks.
Automatically building research reading lists
TLDR
This work explores several methods for augmenting existing collaborative and content-based filtering algorithms with measures of the influence of a paper within the web of citations, including a novel method for using importance scores to influence collaborative filtering.
Towards a personalized, scalable, and exploratory academic recommendation service
TLDR
A web service called thevisor is presented which helps the users build a strong bibliography by extending the document set obtained after a first-level search by featuring an efficient and personalized recommendation algorithm and features result diversification, relevance feedback, visualization for exploratory search.
Research-paper recommender systems: a literature survey
TLDR
Several actions could improve the research landscape: developing a common evaluation framework, agreement on the information to include in research papers, a stronger focus on non-accuracy aspects and user modeling, a platform for researchers to exchange information, and an open-source framework that bundles the available recommendation approaches.
Enhancing digital libraries with TechLens
TLDR
This paper presents and experiments with hybrid recommender algorithms that combine collaborative filtering and content-based filtering to recommend research papers to users and shows that users value paper recommendations, that the hybrid algorithms can be successfully combined, and that these results can be applied to develop recommender systems for other types of digital libraries.
...
1
2
...