Please use this identifier to cite or link to this item:
Title: Using Query Expansion Techniques and Content-Based Filtering for Personalizing Analysis in Big Data
Authors: Menaceur, Sadek 
Derdour, Makhlouf 
Bouramoul, Abdelkrim 
Affiliations: Faculty of Information and Communication Technology (ICT) 
Keywords: Big Data;OLAP
Issue Date: Mar-2020
Journal: International Journal of Information Technology and Web Engineering (IJITWE) 
Volume: Vol.15
Issue: Issue 2
Start page: 77
End page: 101
The recent debates on personalizing analyses in a Big Data context are one of the most solicited challenges for business intelligence (BI) administrators. The high-volume, the high-variety, and the high-velocity of Big Data have produced difficulty in storing, processing, and analyzing data in traditional systems. These 3Vs (volume, velocity, and variety) created many new challenges and make them difficult to extract the specific needs of the users. In addition, the user may be faced with the problem of disorientation; he does not know what information really corresponds to his needs. The information personalization systems aim to overcome these problems of disorientation by using a user profile. The effectiveness of the personalization system in a Big Data context is to demonstrate by the relevance and accuracy of the content of the results obtained, according to the needs of the user and the context of the research. Nevertheless, most of the recent research focused on the relational data warehouse personalizing and ignored the integration of the user context into the analysis of OLAP cubes, which is the first concerned to execute the user's multidimensional queries. To deal with this, the authors propose in this article a dynamic personalizing approach in Big Data context using OLAP cubes, based on the Content-Based Filtering, and the Query Expansion techniques. The first step in the proposal consists of processing the user queries by an enrichment technique in order to integrate the user profile and his searching context to reduce the searching space in the OLAP cube, and use the expansion technique to extend the scope of the analysis in the OLAP cube. The retrieved results are: “as relevant as possible” compared to the user's initial request. Afterward, they use information filtering techniques such as content-based filtering to personalize the analysis in the reduced data cube according to the term frequency and cosine similarity. Finally, they present a case study and experiences results to evaluate and validate their approach.
DOI: 10.4018/IJITWE.2020040104
Appears in Collections:Journal Articles

Files in This Item:
File Description SizeFormat
ijitwe.webp7.76 kBUnknownView/Open
Show full item record

Page view(s)

Last Week
Last month
checked on Nov 24, 2020


checked on Nov 24, 2020

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.