Research Article
Design and Development of an Intelligent Semantic Recommendation System for Websites
@INPROCEEDINGS{10.1007/978-3-030-48513-9_16, author={Zhiqiang Zhang and Heping Yang and Di Yang and Xiaowei Jiang and Nan Chen and Mingnong Feng and Ming Yang}, title={Design and Development of an Intelligent Semantic Recommendation System for Websites}, proceedings={Cloud Computing, Smart Grid and Innovative Frontiers in Telecommunications. 9th EAI International Conference, CloudComp 2019, and 4th EAI International Conference, SmartGIFT 2019, Beijing, China, December 4-5, 2019, and December 21-22, 2019}, proceedings_a={CLOUDCOMP}, year={2020}, month={6}, keywords={Ontology Vertical search engine Semantic expansion System design}, doi={10.1007/978-3-030-48513-9_16} }- Zhiqiang Zhang
Heping Yang
Di Yang
Xiaowei Jiang
Nan Chen
Mingnong Feng
Ming Yang
Year: 2020
Design and Development of an Intelligent Semantic Recommendation System for Websites
CLOUDCOMP
Springer
DOI: 10.1007/978-3-030-48513-9_16
Abstract
When searching for the interesting content within a specific website, how to describe the initial need by selecting proper keywords is a critical problem. The character-matching search functions of website can hardly meet users’ requirements. Furthermore, building the content of webpages of a specific web-site and the associated rules is uneconomical. This paper, based on the framework of the Lucene engine, applied a semantic ontology, the calculation of the relevance of word entries, and the semantics of keywords to design an intelligent semantic recommendation system with the Jena secondary semantic analysis technique. Subsequently, the expanded keywords were semantically ranked based on the term frequency analysis technique. Meanwhile, the ontology algorithm and their relevance were introduced as the dynamic weight values. Finally, in the text content retrieval process, the search results were ranked based on the previous relevance weights. The experimental results show that the system designed in this paper is not only easy to develop but also capable of expanding users queries and recommending relevant content. Further, the system can improve the precision and recall for website search results.
