Finding Related Papers in Literature Digital Libraries

Ratprasartporn, Nattakarn; Özsoyoǧlu, Gültekin

doi:10.1007/978-3-540-74851-9_23

Cited by 12 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the remaining analysis, these 19 approaches are ignored. Of the remaining 70 approaches, 48 approaches (69%), were evaluated using an offline evaluation 54,58,59,74,78,80,83,86,[88][89][90][91][92][94][95][96][97][98][99][100][102][103][104][105][106][107]109], 24 approaches (34%) with a user study [66][67][68][69][70][71][72][73][74]76,77,79,81,82,87,[102][103][104][105][106][107][108]110], five approaches (7%) were evaluated in real-world systems...…”

Section: Evaluation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Research paper recommender system evaluation

Beel¹,

Langer²,

Genzmehr³

et al. 2013

Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation

116

View full text Add to dashboard Cite

Over 80 approaches for academic literature recommendation exist today. The approaches were introduced and evaluated in more than 170 research articles, as well as patents, presentations and blogs. We reviewed these approaches and found most evaluations to contain major shortcomings. Of the approaches proposed, 21% were not evaluated. Among the evaluated approaches, 19% were not evaluated against a baseline. Of the user studies performed, 60% had 15 or fewer participants or did not report on the number of participants. Information on runtime and coverage was rarely provided. Due to these and several other shortcomings described in this paper, we conclude that it is currently not possible to determine which recommendation approaches for academic literature are the most promising. However, there is little value in the existence of more than 80 approaches if the best performing approaches are unknown.

show abstract

Section: Evaluation Methodsmentioning

confidence: 99%

“…Seven approaches (15%) were evaluated using other measures [88][89][90][91]97,98,105]. Overall, results of the different measures highly correlated -that is algorithms, which performed well using precision also performed well using, for instance, NDCG.…”

Section: Use Of Offline Evaluation Metricsmentioning

confidence: 99%

Research paper recommender system evaluation

Beel¹,

Langer²,

Genzmehr³

et al. 2013

Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation

116

View full text Add to dashboard Cite

show abstract

“…There are several research paper recommendation methods which focus on finding similarity between research articles [14]. These methods include: (1) collaborative filtering [15] (2) meta-data based [16], [17] (3) content-based [18], [19] (4) citation-based [9], [10], [20], [21] (5) multi-level citation network [13] (6) and 7user profile-based [22]- [24] approaches.…”

Section: Related Workmentioning

confidence: 99%

“…Content-based [18], [19] approaches find relationship between two papers by matching their contents. It gives improved results and is proven to be a better option than merely relying on meta-data based techniques.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Approach Toward Research Paper Recommendation Using Centrality Measures and Author Ranking

et al. 2019

View full text Add to dashboard Cite

The volume of research articles in digital repositories is increasing. This spectacular growth of repositories makes it rather difficult for researchers to obtain related research papers in response to their queries. The problem becomes worse when a researcher with insufficient knowledge of searching research articles uses these repositories. In the traditional recommendation approaches, the results of the query miss many high-quality papers, in the related work section, which are either published recently or have low citation count. To overcome this problem, there needs to be a solution which considers not only structural relationships between the papers but also inspects the quality of authors publishing those articles. Many research paper recommendation approaches have been implemented which includes collaborative filtering-based, content-based, and citation analysis-based techniques. The collaborative filtering-based approaches primarily use paper-citation matrix for recommendations, whereas the content-based approaches only consider the content of the paper. The citation analysis considers the structure of the network and focuses on papers citing or cited by the paper of interest. It is therefore very difficult for a recommender system to recommend high-quality papers without a hybrid approach that incorporates multiple features, such as citation information and author information. The proposed method creates a multilevel citation and relationship network of authors in which the citation network uses the structural relationship between the papers to extract significant papers, and authors' collaboration network finds key authors from those papers. The papers selected by this hybrid approach are then recommended to the user. The results have shown that our proposed method performs exceedingly well as compared with the state-of-the-art existing systems, such as Google scholar and multilevel simultaneous citation network.

show abstract

“…The content-based techniques use content similarity techniques to measure the relatedness of two papers [12,13]. Using content to determine the similarity between research papers provides much better results compared to using only the citations.…”

Section: Related Workmentioning

confidence: 99%

Paper recommendation using citation proximity in bibliographic coupling

Habib¹,

Afzal²

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:Research paper recommendation has been a hot research area for the last few decades. Thus far, numerous different paper recommendation approaches have been proposed. Some of these include methods based on metadata, content similarity, collaborative filtering, and citation analysis, among others. Citation analysis methods include bibliographic coupling and co-citation analysis. Much research has been done in the area of co-citation analysis.Researchers have also performed experiments using the proximity of in-text citations in co-citation analysis and have found that it improves the accuracy of paper recommendation. In co-citation analysis, the similarity is discovered based on the frequency of co-cited papers in different research papers and those citing papers may belong to different areas. However, when proximity is used to calculate co-citation, the accuracy of recommendations improves significantly.Bibliographic coupling finds bibliographic coupling strength based on the common references between two papers. In bibliographic coupling, a large number of common references of two papers means that they belong to the same area, unlike co-citation analysis, in which there is a possibility that the citing papers may belong to different areas. Based on the observation that with the use of proximity analysis the accuracy in cases of co-citation analysis has improved, this paper investigates if the accuracy of paper recommendation can be further improved by using proximity analysis in bibliographic coupling. This paper proposes an approach that extends the traditional bibliographic coupling by exploiting the proximity of in-text citations of bibliographically coupled articles. The proposed approach takes into account the proximity of in-text citations by clustering the in-text citations using a density-based algorithm called DBSCAN. Experiments on a data set of research papers are presented to show that there is a substantial increase in accuracy of the recommendations produced by DBSCAN based on proximity analysis of in-text citations compared to traditional bibliographic coupling and content-based approaches.

show abstract

Finding Related Papers in Literature Digital Libraries

Cited by 12 publications

References 11 publications

Research paper recommender system evaluation

Research paper recommender system evaluation

A Hybrid Approach Toward Research Paper Recommendation Using Centrality Measures and Author Ranking

Paper recommendation using citation proximity in bibliographic coupling

Contact Info

Product

Resources

About