Please use this identifier to cite or link to this item:
Title: Improving Social Book Search Using Structure Semantics, Bibliographic Descriptions and Social Metadata
Authors: Ullah, Irfan
Keywords: Sciences
Computer Sciences
Computer & IT
Issue Date: 2020
Publisher: University of Peshawar, Peshawar.
Abstract: The emergence of the Social Web and social collaborative cataloging web applications have changed the way books are described, discovered and accessed. These applications present books not only through the bibliographic descriptions or professional metadata but also allow users to describe these resources through user-generated content or social metadata. This social practice has attracted researchers under the broader topic of Social Book Search to make it part of the book retrieval process aiming to improve the relevance of search results and understand the impact of the Social Web on the search performance. For this purpose, the classical Information Retrieval (IR) approaches are employed to produce an initial set of search results, which are re-ranked using the social metadata to see if the search relevance gets improved. Although numerous studies found that the social metadata improves over the baseline run, they are unable to exploit fully the potential role of the query-document representation and weighting model, which questions the credibility of such a conclusion. Also, in re-ranking, most of the studies evaluated and compared different metadata features to produce better search results but remained silent about the final shape of re-ranking. To fill these gaps in the literature, this research work considers the contribution of the querydocument representation and weighting model to the fullest to produce a strong classical baseline run and re-ranks it using a multifeatured fusion of different social metadata features. Our best-performing baseline and re-ranking runs outperform the existing approaches on several topics sets and relevance judgments. The findings suggest that the best document representation can be achieved if the social metadata is made part of the search index. The best query representation is achieved using all-topic-fields. The relevance of search results improves with re-ranking the best-performing baseline runs. These findings have implications for researchers working in Libraries, Information Science, IR, and Interactive IR.
Gov't Doc #: 19864
Appears in Collections:PhD Thesis of All Public / Private Sector Universities / DAIs.

Files in This Item:
File Description SizeFormat 
Irfan Ullah CS 2020 uni of peshwar prr.pdf6.46 MBAdobe PDFView/Open

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