A Group Recommender System for Selecting Experts to Review a Specific Problem

Hoang, Dinh Tuyen; Nguyên, Ngoc Thanh; Hwang, Dosam

doi:10.1007/978-3-319-98443-8_25

Cited by 6 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RSs in scholarly communities have been used in number of fields such as paper recommendation (Haruna et al , 2017; Gori and Pucci, 2006; Chenguang and Wenxin, 2010; Zhiping and Linna, 2010; Beel et al , 2013; Mishra, 2012; Bancu et al , 2012), expert and reviewer recommendation (Reichling and Wulf, 2009; Hoang et al , 2018; Protasiewicz et al , 2016; KardanA and Aghahadi, 2013; Davoodi et al , 2013; Yunhong and Xianli, 2016). To the best of our knowledge no SLR study has been conducted on scholarly publication venue RSs papers.…”

Section: Background and Related Workmentioning

confidence: 99%

Scholarly publication venue recommender systems

Dehdarirad

Ghazimirsaeid

Jalalimanesh

2020

DTA

View full text Add to dashboard Cite

PurposeThe purpose of this investigation is to identify, evaluate, integrate and summarize relevant and qualified papers through conducting a systematic literature review (SLR) on the application of recommender systems (RSs) to suggest a scholarly publication venue for researcher's paper.Design/methodology/approachTo identify the relevant papers published up to August 11, 2018, an SLR study on four databases (Scopus, Web of Science, IEEE Xplore and ScienceDirect) was conducted. We pursued the guidelines presented by Kitchenham and Charters (2007) for performing SLRs in software engineering. The papers were analyzed based on data sources, RSs classes, techniques/methods/algorithms, datasets, evaluation methodologies and metrics, as well as future directions.FindingsA total of 32 papers were identified. The most data sources exploited in these papers were textual (title/abstract/keywords) and co-authorship data. The RS classes in the selected papers were almost equally used. DBLP was the main dataset utilized. Cosine similarity, social network analysis (SNA) and term frequency–inverse document frequency (TF–IDF) algorithm were frequently used. In terms of evaluation methodologies, 24 papers applied only offline evaluations. Furthermore, precision, accuracy and recall metrics were the popular performance metrics. In the reviewed papers, “use more datasets” and “new algorithms” were frequently mentioned in the future work part as well as conclusions.Originality/valueGiven that a review study has not been conducted in this area, this paper can provide an insight into the current status in this area and may also contribute to future research in this field.

show abstract