Understanding and Predicting Question Subjectivity in Social Question and Answering

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The explosive popularity of social networking sites has provided an additional venue for online information seeking. By posting questions in their status updates, more and more people are turning to social networks to fulfill their information needs. Given that understanding individuals' information needs could improve the performance of question answering, in this paper, we model the task of intent detection as a binary classification problem, and thus for each question, two classes are defined: subjective and objective. We use a comprehensive set of lexical, syntactical, and contextual features to build the classifier and the experimental results show satisfactory classification performance. By applying the classifier on a larger dataset, we then present in-depth analyses to compare subjective and objective questions, in terms of the way they are being asked and answered. We find that the two types of questions exhibited very different characteristics, and further validate the expected benefits of differentiating questions according to their subjectivity orientations.

Original languageEnglish
Article number7495049
Pages (from-to)32-41
Number of pages10
JournalIEEE Transactions on Computational Social Systems
Volume3
Issue number1
DOIs
Publication statusPublished - 1 Mar 2016

Fingerprint

subjectivity
Classifiers
Classifier
Binary Classification
Social Networking
Question Answering
Large Data Sets
Classification Problems
Social Networks
performance
popularity
networking
social network
Update
present
Experimental Results
Model
Class
Syntax

Keywords

  • Information seeking
  • social question and answering (social Q&A)
  • social search
  • subjectivity analysis social network
  • Twitter

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Modelling and Simulation
  • Social Sciences (miscellaneous)

Cite this

Understanding and Predicting Question Subjectivity in Social Question and Answering. / Liu, Zhe; Jansen, Bernard.

In: IEEE Transactions on Computational Social Systems, Vol. 3, No. 1, 7495049, 01.03.2016, p. 32-41.

Research output: Contribution to journalArticle

@article{61df175a9f4940e08d8390d0acad988b,
title = "Understanding and Predicting Question Subjectivity in Social Question and Answering",
abstract = "The explosive popularity of social networking sites has provided an additional venue for online information seeking. By posting questions in their status updates, more and more people are turning to social networks to fulfill their information needs. Given that understanding individuals' information needs could improve the performance of question answering, in this paper, we model the task of intent detection as a binary classification problem, and thus for each question, two classes are defined: subjective and objective. We use a comprehensive set of lexical, syntactical, and contextual features to build the classifier and the experimental results show satisfactory classification performance. By applying the classifier on a larger dataset, we then present in-depth analyses to compare subjective and objective questions, in terms of the way they are being asked and answered. We find that the two types of questions exhibited very different characteristics, and further validate the expected benefits of differentiating questions according to their subjectivity orientations.",
keywords = "Information seeking, social question and answering (social Q&A), social search, subjectivity analysis social network, Twitter",
author = "Zhe Liu and Bernard Jansen",
year = "2016",
month = "3",
day = "1",
doi = "10.1109/TCSS.2016.2564400",
language = "English",
volume = "3",
pages = "32--41",
journal = "IEEE Transactions on Computational Social Systems",
issn = "2329-924X",
publisher = "IEEE Systems, Man, and Cybernetics Society",
number = "1",

}

TY - JOUR

T1 - Understanding and Predicting Question Subjectivity in Social Question and Answering

AU - Liu, Zhe

AU - Jansen, Bernard

PY - 2016/3/1

Y1 - 2016/3/1

N2 - The explosive popularity of social networking sites has provided an additional venue for online information seeking. By posting questions in their status updates, more and more people are turning to social networks to fulfill their information needs. Given that understanding individuals' information needs could improve the performance of question answering, in this paper, we model the task of intent detection as a binary classification problem, and thus for each question, two classes are defined: subjective and objective. We use a comprehensive set of lexical, syntactical, and contextual features to build the classifier and the experimental results show satisfactory classification performance. By applying the classifier on a larger dataset, we then present in-depth analyses to compare subjective and objective questions, in terms of the way they are being asked and answered. We find that the two types of questions exhibited very different characteristics, and further validate the expected benefits of differentiating questions according to their subjectivity orientations.

AB - The explosive popularity of social networking sites has provided an additional venue for online information seeking. By posting questions in their status updates, more and more people are turning to social networks to fulfill their information needs. Given that understanding individuals' information needs could improve the performance of question answering, in this paper, we model the task of intent detection as a binary classification problem, and thus for each question, two classes are defined: subjective and objective. We use a comprehensive set of lexical, syntactical, and contextual features to build the classifier and the experimental results show satisfactory classification performance. By applying the classifier on a larger dataset, we then present in-depth analyses to compare subjective and objective questions, in terms of the way they are being asked and answered. We find that the two types of questions exhibited very different characteristics, and further validate the expected benefits of differentiating questions according to their subjectivity orientations.

KW - Information seeking

KW - social question and answering (social Q&A)

KW - social search

KW - subjectivity analysis social network

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84976534300&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976534300&partnerID=8YFLogxK

U2 - 10.1109/TCSS.2016.2564400

DO - 10.1109/TCSS.2016.2564400

M3 - Article

VL - 3

SP - 32

EP - 41

JO - IEEE Transactions on Computational Social Systems

JF - IEEE Transactions on Computational Social Systems

SN - 2329-924X

IS - 1

M1 - 7495049

ER -