Building recommender systems for scholarly information

Hristakeva, Maya; Kershaw, Daniel; Rossetti, Marco; Knoth, Petr; Pettit, Benjamin; Vargas, Saúl; Jack, Kris

doi:10.1145/3057148.3057152

Cited by 13 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They require as input exactly one reference string per line (e.g. ParsCit [4]). Extracting candidate citations with exactly one citation per line is challenging, as many tools that extract text from formats such as PDF either preserve hard line breaks, or attempt to wrap the text, which works well for running paragraphs, but tends to glom multiple citations together (e.g.…”

Section: Related Work and Discussionmentioning

confidence: 99%

“…With over 1 million papers published each year [2] and an estimated 10% year on year increase in the annual number of these outputs [3], researchers need tools to help them decide what to read. While recommendation systems for academic papers, such as those provided by Google Scholar, Mendeley Suggest [4] or CORE [5,6] have been created to address the problem of discovering relevant literature, more can be done to help users to effectively navigate through the network of scientific papers. One traditional yet effective way of discovering new and relevant content is by following the edges of the citation graph in the opposite direction, i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

What Others Say About This Work? Scalable Extraction of Citation Contexts from Research Papers

Knoth

Gooch

Jack

2017

Research and Advanced Technology for Digital Libraries

Self Cite

View full text Add to dashboard Cite

Abstract. This work presents a new, scalable solution to the problem of extracting citation contexts: the textual fragments surrounding citation references. These citation contexts can be used to navigate digital libraries of research papers to help users in deciding what to read. We have developed a prototype system which can retrieve, on-demand, citation contexts from the full text of over 15 million research articles in the Mendeley catalog for a given reference research paper. The evaluation results show that our citation extraction system provides additional functionality over existing tools, has two orders of magnitude faster runtime performance, while providing a 9% improvement in F-measure over the current state-of-the-art.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

What Others Say About This Work? Scalable Extraction of Citation Contexts from Research Papers

Knoth

Gooch

Jack

2017

Research and Advanced Technology for Digital Libraries

Self Cite

View full text Add to dashboard Cite

show abstract

“…Regarding the publication time awareness, while the concept of time has previously used in RS to better define and delimit long-term vs. short-term user preferences [13], and to suggest papers to users with no previous activity (i.e., new users) [15], [16]. To the best of our knowledge, only [12] has addressed the problem of recommending the most recently published scientific work (i.e., new papers).…”

Section: Related Workmentioning

confidence: 99%

Capturing and Exploiting Citation Knowledge for Recommending Recently Published Papers

Khadka

Cantador

Fernández

2020

2020 IEEE 29th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE)

View full text Add to dashboard Cite

With the continuous growth of scientific literature, discovering relevant academic papers for a researcher has become a challenging task, especially when looking for the latest, most recent papers. In this case, traditional collaborative filtering systems are ineffective, since they are unable to recommend items not previously seen, rated or cited. In this paper, we explore the potential of exploiting citation knowledge to provide a given user with relevant suggestions about recent scientific publications. A novel hybrid recommendation method that encapsulates such citation knowledge is proposed. Experimental results show improvements over baseline methods, evidencing benefits of using citation knowledge to recommend recently published papers in a personalised way. Moreover, as a result of our work, we also provide a unique dataset that, differently to previous corpora, contains detailed paper citation information.

show abstract

“…The current platform partner of Mr. DLib is the reference-management software JabRef [23,24]. The current research partner of Mr. DLib is CORE [25][26][27]. Mr. DLib acts as an intermediate between these partners.…”

Section: Mr Dlib's Scholarly Living Labmentioning

confidence: 99%

Online Evaluations for Everyone: Mr. DLib’s Living Lab for Scholarly Recommendations

Beel

Collins

Kopp

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We introduce the first 'living lab' for scholarly recommender systems. This lab allows recommender-system researchers to conduct online evaluations of their novel algorithms for scholarly recommendations, i.e., recommendations for research papers, citations, conferences, research grants, etc. Recommendations are delivered through the living lab's API to platforms such as reference management software and digital libraries. The living lab is built on top of the recommender-system as-a-service Mr. DLib. Current partners are the reference management software JabRef and the CORE research team. We present the architecture of Mr. DLib's living lab as well as usage statistics on the first sixteen months of operating it. During this time, 1,826,643 recommendations were delivered with an average click-through rate of 0.21%.

show abstract

Building recommender systems for scholarly information

Cited by 13 publications

References 13 publications

What Others Say About This Work? Scalable Extraction of Citation Contexts from Research Papers

What Others Say About This Work? Scalable Extraction of Citation Contexts from Research Papers

Capturing and Exploiting Citation Knowledge for Recommending Recently Published Papers

Online Evaluations for Everyone: Mr. DLib’s Living Lab for Scholarly Recommendations

Contact Info

Product

Resources

About