SLIIT >
Research Symposium >
SLIIT Student Research -2017 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/529

Title: Ontology – based News Finder for Visually Impaired Citizens
Authors: Dissanayaka, R.C.P.
Welikala, H.D.
Thabrew, K.B.P.
Perdinandis, R.S.K.I.P.
Rajapaksha, S.
Keywords: Ontology
Agent
User profile
Concept comparison tool
Issue Date: 2017
Publisher: SLIIT
Series/Report no.: ;17-088
Abstract: Reading newspapers has become a significant day to day activity of majority of the people because it has an effect on human lifestyle and will help deciding their activities planned for the future. Therefore, it is focused on providing an ontology based solution to the visually impaired citizens to access the most relevant and accurate news articles without a hesitation through voice media. It is an advantage for them to get the articles which satisfy their requirement and preferences without wasting time and money. A system which can gather news items based on user request from various news providers which are in different sources and deliver the result to the user in a personalized format of news articles provides the solution to the above matter. The designed system gathers news items from news websites through agents and stores those articles as instances in news ontology. After that the instances are compared among themselves using concept comparison tool to present the reader the article with highest accuracy which indicate the most relevant search results. And system recommends news through a user profiling mechanism. The input is taken through voice format from the client-side android mobile application, converted into text format and special keywords were extracted by semantic analyzer. Those key words are sent to sever to perform the mentioned process and final output is returned back to client. That final output also delivered in voice format. The research project is evaluated using many evaluation techniques. Ontology created is assessed by Ontology correctness using accuracy, completeness, consistency of the ontology and ontology quality using computational efficiency, adaptability and clarity. Accuracy of the final result was determined by comparing the instances of the ontology with each other to find the accurate answer by considering the result with highest occurrence.
URI: http://hdl.handle.net/123456789/529
Appears in Collections:SLIIT Student Research -2017

Files in This Item:

File Description SizeFormat
17_088.pdf370.56 kBAdobe PDFView/Open
View Statistics

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

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback