International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 7 |
Published: February 2024 |
Authors: Tolulope Anthonia Adebayo, Bolanle Adefowoke Ojokoh |
![]() |
Tolulope Anthonia Adebayo, Bolanle Adefowoke Ojokoh . Prescriptive Analytics for Publication Venue Recommendation. International Journal of Computer Applications. 186, 7 (February 2024), 11-17. DOI=10.5120/ijca2024923397
@article{ 10.5120/ijca2024923397, author = { Tolulope Anthonia Adebayo,Bolanle Adefowoke Ojokoh }, title = { Prescriptive Analytics for Publication Venue Recommendation }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 7 }, pages = { 11-17 }, doi = { 10.5120/ijca2024923397 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A Tolulope Anthonia Adebayo %A Bolanle Adefowoke Ojokoh %T Prescriptive Analytics for Publication Venue Recommendation%T %J International Journal of Computer Applications %V 186 %N 7 %P 11-17 %R 10.5120/ijca2024923397 %I Foundation of Computer Science (FCS), NY, USA
Publication venue recommendation provide answers to one of the major challenges researchers face while seeking to get their research results or findings published in high-valued journals and conferences for easy dissemination and to maximize effects on future research. However, most recommendation systems available use traditional approaches which encounter problems such as cold start, data sparsity, among others. Hence, this study proposes a two-level recommendation model using prescriptive analytics technique (fuzzy logic) algorithm to infer decision on a suitable venue for publication based on key parameters such as the cost of publishing, impact factor of a journal or rank of a conference, and the average duration of review. Experiments were carried out on real world dataset obtained from Digital Bibliography and Library Project (DBLP) and Aminer Digital repositories. Results obtained from the evaluation of the system in terms of Accuracy@N, Precision, and F1-measure shows that the system performed efficiently and provides effective recommendation.