An Architecture of an Academic Search Engine with Personalized Search Result Ranking Mechanism

A rapid increasing of information on the Internet and World Wide Web causes information overloaded problem. Thus, search engines become important tools to help WWW users to discover the information they need. With an exponentially increasing of published research paper, community-based research paper sharing systems and academic search engines become indispensable tools for researchers to search for any research papers in their fields of expertise and related fields according to their interests. To improve a quality of research paper searching, an academic search engines' capability should be enhanced. This paper proposed an architecture of an academic search engine with personalized search result ranking mechanism. To evaluate the performance of personalized search result ranking mechanism, twenty-five graduate students were invited to be participants in this research study. As a criterion, the participants were asked to use a prototype of academic search engine to find and bookmark any research papers according to their interests. This would guarantee that each participants' list of interesting research paper could be recorded. The Normalized Discounted Cumulative Gain (NDCG) was used as a metric to determine that performance of personalized search result ranking mechanism. During the experiment, each participant was asked to search for research papers according to their interests. The result of the experiment suggested that the personalized search result ranking mechanism outperformed the original search result ranking. Hence, the proposed architecture of the academic search engine with personalized search engine mechanism does benefit a tasks of research paper discovery. It improves the quality of research paper searching.

[1]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[2]  Siripun Sanguansintukul,et al.  A comparison of search engine using “tag title and abstract” with CiteULike — An initial evaluation , 2009, 2009 International Conference for Internet Technology and Secured Transactions, (ICITST).

[3]  Jie Tang,et al.  AMiner: Toward Understanding Big Scholar Data , 2016, WSDM.

[4]  S. Sanguansintukul,et al.  Improving research paper searching with social tagging — A preliminary investigation , 2009, 2009 Eighth International Symposium on Natural Language Processing.

[5]  John Riedl,et al.  Tagsplanations: explaining recommendations using tags , 2009, IUI.

[6]  Eric Brill,et al.  Beyond PageRank: machine learning for static ranking , 2006, WWW '06.

[7]  Wei-Ying Ma,et al.  Optimizing web search using web click-through data , 2004, CIKM '04.

[8]  References , 1971 .

[9]  Xiaoming Li,et al.  A Paper Recommender for Scientific Literatures Based on Semantic Concept Similarity , 2008, ICADL.

[10]  Djoerd Hiemstra,et al.  Retrieving Web Pages Using Content, Links, URLs and Anchors , 2001, TREC.

[11]  Sean M. McNee,et al.  On the recommending of citations for research papers , 2002, CSCW '02.

[12]  Stephen E. Robertson,et al.  Effective site finding using link anchor information , 2001, SIGIR '01.

[13]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR '00.

[14]  W. Bruce Croft,et al.  The History of Information Retrieval Research , 2012, Proceedings of the IEEE.

[15]  Russell Beale,et al.  Sharing vocabularies: tag usage in CiteULike , 2008, BCS HCI.

[16]  Kevin S. McCurley,et al.  Analysis of anchor text for web search , 2003, SIGIR.

[17]  Worasit Choochaiwattana,et al.  Usage of tagging for research paper recommendation , 2010, 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE).

[18]  Emi Ishita,et al.  A search engine for Japanese academic papers , 2010, JCDL '10.

[19]  Antal van den Bosch,et al.  Recommending scientific articles using citeulike , 2008, RecSys '08.

[20]  Zhaohui Wu,et al.  Towards better understanding of academic search , 2016, 2016 IEEE/ACM Joint Conference on Digital Libraries (JCDL).

[21]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[22]  Ümit V. Çatalyürek,et al.  TheAdvisor: a webservice for academic recommendation , 2013, JCDL '13.

[23]  Michael B. Spring,et al.  Applying Social Annotations to Retrieve and Re-rank Web Resources , 2009, 2009 International Conference on Information Management and Engineering.