Ranking Documents Based on the Semantic Relations Using Analytical Hierarchy Process: Query Expansion and Ranking Process

Ranking Documents Based on the Semantic Relations Using Analytical Hierarchy Process: Query Expansion and Ranking Process

Ali I. El-Dsouky, Hesham A. Ali, Rabab Samy Rashed
Copyright: © 2017 |Pages: 16
DOI: 10.4018/IJIRR.2017070102
(Individual Articles)
No Current Special Offers


With the rapid growth of the World Wide Web comes the need for a fast and accurate way to reach the information required. Search engines play an important role in retrieving the required information for users. Ranking algorithms are an important step in search engines so that the user could retrieve the pages most relevant to his query In this work, the authors present a method for utilizing genealogical information from ontology to find the suitable hierarchical concepts for query extension, and ranking web pages based on semantic relations of the hierarchical concepts related to query terms, taking into consideration the hierarchical relations of domain searched (sibling, synonyms and hyponyms) by different weighting based on AHP method. So, it provides an accurate solution for ranking documents when compared to the three common methods.
Article Preview

Search engines accuracy is improved based on how they will search for the meaning of query terms, and how they will present the results to users by evaluating the documents containing the query terms. There are many solutions for improving the search engine: by expanding query taking into account the semantic meaning related to user’s query terms; or by improving the evaluation of documents not only by the occurrence of terms, but also by how it semantically relates to the topic search.

Query expansion (QE) is a technique used to aid users to express their requirements. There are many works in QE techniques, such as the mechanisms of relevance feedback (Lin, Lin & He, 2012), and statistical term co-occurrence (Chu, Liu & Mao, 2002). The drawback of relevance feedback and statistical term co-occurrence methods is the analysis of pervious results documents which may provide a relationship between extracted terms and the original query. But this cannot be ensured if there are no sufficient documents used for analysis before a search process.

The semantic meaning is a method based on ontology to disambiguate the query meaning (Vizcaíno, García, Caballero et al., 2012). This method is used to expand query terms by their synonyms using WordNet ontology, or by adding synonyms and terms related to them based on ontology domain. But adding these terms to query without taking into consideration their hierarchical relationships may affect the relevance of documents to the main query terms (Tyagi & Sharma, 2012).

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2024)
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing