SemAcSearch: A semantically modeled academic search engine

Abstract

Scholarly article search is a new vertical search paradigm that has gained popularity fast, due in part to the large volumes of research output from universities across the globe. The ranking given to scholarly articles on a search engine's result page is a significant factor in determining its citation rate and audience. A higher Search Engine(SE) rank can help in garnering more reads and possibly more citations for an article, while a lower rank can actually hinder the perceived value of an article from the users' perspective. Hence, searching academic journals and scholarly articles may need special consideration to other factors, beyond the keyword search and context-based querying strategies adopted by most conventional search engines. Academic search engine optimization (ASEO) is a crucial requirement for search engines dealing with scholarly articles. In this paper, we present a specialized, vertical search engine focusing on journal and scholarly article search, that considers context and semantics of the query and articles in computing the overall ranking of publications. Using this, the effectiveness of various ranking algorithms in determining the rank of individual articles was explored and their performance compared. © 2017 IEEE.