A Paper Recommendation System Based on User Interest and Citations

Bulut, Betül; Kaya, Buket; Kaya, Mehmet

doi:10.1109/ubmyk48245.2019.8965533

Cited by 6 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Users can be modelled as a combination of features of papers they interacted with [19,21], e.g. their clicked [26] or authored publications [22]. Papers can for example be represented by their textual content [88].…”

Section: Problem Statementmentioning

confidence: 99%

“…Some approaches derived user profiles from users' written papers: authored papers [5,21,22,55,63,[74][75][76]116], a partitioning of authored papers [27], research fields of authored papers [41] and referenced papers [116].…”

Section: User Profilementioning

confidence: 99%

“…For author-based popularity measures we found unspecified ones [65] such as authority [116] as well as ones regarding the citations an author received: citation count of papers [22,96,108,119], change in citation count [25,26], annual citation count [26], number of citations related to papers [59], h-index [26]. We found two definitions of author's popularity using the graph structure of scholarly networks, namely the number of co-authors [41] and a person's centrality [108].…”

Section: Popularitymentioning

confidence: 99%

“…For paper-based popularity measures we encountered some citation-based definitions such as vitality [117], citation [22] and theirs centrality [96] in the citation network. Additionally, some approaches incorporated less formal interactions: number of downloads [56], social media mentions [119] and normalised number of bookmarks [84].…”

Section: Popularitymentioning

confidence: 99%

See 3 more Smart Citations

Scientific paper recommendation systems: a literature review of recent publications

Kreutz

Schenkel

2022

Int J Digit Libr

View full text Add to dashboard Cite

Scientific writing builds upon already published papers. Manual identification of publications to read, cite or consider as related papers relies on a researcher’s ability to identify fitting keywords or initial papers from which a literature search can be started. The rapidly increasing amount of papers has called for automatic measures to find the desired relevant publications, so-called paper recommendation systems. As the number of publications increases so does the amount of paper recommendation systems. Former literature reviews focused on discussing the general landscape of approaches throughout the years and highlight the main directions. We refrain from this perspective, instead we only consider a comparatively small time frame but analyse it fully. In this literature review we discuss used methods, datasets, evaluations and open challenges encountered in all works first released between January 2019 and October 2021. The goal of this survey is to provide a comprehensive and complete overview of current paper recommendation systems.

show abstract

Section: Problem Statementmentioning

confidence: 99%

Section: User Profilementioning

confidence: 99%

Section: Popularitymentioning

confidence: 99%

Section: Popularitymentioning

confidence: 99%

See 2 more Smart Citations

Scientific paper recommendation systems: a literature review of recent publications

Kreutz

Schenkel

2022

Int J Digit Libr

View full text Add to dashboard Cite

show abstract

“…Bulut et al, [13] conducted a study on recommending papers based on user profile and bibliographic approach. The dataset created from the metadata is used for creating a user profile after undergoing certain preprocessing.…”

Section: Literature Reviewmentioning

confidence: 99%

A Citation Recommendation System Using Deep Reinforcement Learning

Nair

Paul

George

2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Recommender systems have seen tremendous growth in the last few years due to the emergence of web services like YouTube, Netflix, and Amazon, etc. An excessive amount of data is being utilized to give proper recommendations to the users. The number of research articles getting published every day is increasing exponentially and thus an efficient model is required to provide accurate and relevant recommendations to the research scholars. The proposed Deep Reinforcement Recommender for Citations (DRRC) model uses reinforcement learning to train the available citation network to achieve the most relevant recommendations. The proposed DRRC model outperforms the state-of-the-art models.

show abstract