Please use this identifier to cite or link to this item:
Title: E-commerce based information retrieval and personalised search
Authors: Camilleri, Anne-Marie (2019)
Keywords: Electronic commerce
Information storage and retrieval systems
Latent semantic indexing
Issue Date: 2019
Citation: Camilleri, A.-M. (2019). E-commerce based information retrieval and personalised search (Bachelor's dissertation).
Abstract: With the evolution of e-commerce websites and internet users over the years, has meant that retailers have to deal with the challenge of information overload while also keeping the customers satisfied. Such specialised systems hence require the retrieval of unstructured information to be able to carry out personalisation on the search results. The main challenges involve retrieving products according to a user's needs using a matching algorithm whereby the user may not be able to express their needs properly within a short query. This task is not an easy one and there is an ever-growing need for efficient information retrieval and personalisation of the search results of such websites. This must also be achieved in an automatic way where the customer's explicit input is not required. This report describes an information retrieval and personalised search system in which different techniques were researched and developed to try achieve the best outcome. The proposed system is split into two components, Information Retrieval and Personalised Search. The information retrieval component is able to retrieve textual information about products from an E-commerce collection and process them in such a way to retrieve the best features. In the personalised search component, a personalisation algorithm is used to convert the user information into the user models. The system is able to re-rank the search results returned by queries made by a user using the retrieved product features and user models. When evaluating our system, we found that using information retrieval techniques such as redLatent Semantic Analysis greatly improves the search result relevance scores. Also, when personalising the search results according to the user's preferences, popularity of the product as well as similarity between the query terms and product description terms, the best results are obtained over all the queries.
Appears in Collections:Dissertations - FacICT - 2019
Dissertations - FacICTAI - 2019

Files in This Item:
File Description SizeFormat 
Anne Marie Camilleri.pdf
  Restricted Access
1.5 MBAdobe PDFView/Open Request a copy

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.