Please use this identifier to cite or link to this item:
Title: Subjectivity Detection through Socio-Linguistic Features
Authors: Younus, Arjumand
Qureshi, M. Atif
Touheed, Nasir
Issue Date: 2011
Publisher: St. Petersburg University Press
Citation: Younus Arjumand. Subjectivity Detection through Socio-Linguistic Features / Arjumand Younus, M. Atif Qureshi, Nasir Touheed // Web of Data: The joint RuSSIR/EDBT 2011 Summer School, August 15–19, 2011, Proceedings of the Fifth Russian Young Scientists Conference in Information Retrieval / B. Novikov, P. Braslavsky (Eds.). — St. Petersburg, 2011 — P. 55-62.
Abstract: Social media platforms have opened new dimensions within the information retrieval domain leading to a novel concept known as Social Information Retrieval. We argue that the concept of Social Information Retrieval can be extended by augmenting the huge amount of content on the traditional Web with the ever-growing rich Social Web content to increase the information richness of today’s search engines. This paper proposes a subjectivity detection framework which can lead towards a proposed emotion-aware search engine interface. Our proposed method differs from previous subjectivity analysis approaches in that it is the first method that takes into account social features of social media platforms for the subjectivity classification task. Through experimental evaluations, we observe the accuracy of the proposed method to be 86.21% which demonstrates a promising outcome for large-scale application of our proposed subjectivity analysis technique.
Conference name: V Russian Summer School in Information Retrieval (RuSSIR’2011)
V Российская летняя школа по информационному поиску (RuSSIR’2011)
EDBT Summer Schools
Conference date: 15.08.2011–19.08.2011
ISBN: 978-5-288-05225-5
Origin: RuSSIR/EDBT2011
Appears in Collections:Информационный поиск

Files in This Item:
File Description SizeFormat 
RuSSIR_2011_06.pdf131,58 kBAdobe PDFView/Open

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