Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features
📝 Abstract
Instead of studying the properties of social relationship from an objective view, in this paper, we focus on individuals’ subjective and asymmetric opinions on their interrelationships. Inspired by the theories from sociolinguistics, we investigate two individuals’ opinions on their interrelationship with their interactive language features. Eliminating the difference of personal language style, we clarify that the asymmetry of interactive language feature values can indicate individuals’ asymmetric opinions on their interrelationship. We also discuss how the degree of opinions’ asymmetry is related to the individuals’ personality traits. Furthermore, to measure the individuals’ asymmetric opinions on interrelationship concretely, we develop a novel model synthetizing interactive language and social network features. The experimental results with Enron email dataset provide multiple evidences of the asymmetric opinions on interrelationship, and also verify the effectiveness of the proposed model in measuring the degree of opinions’ asymmetry.
💡 Analysis
Instead of studying the properties of social relationship from an objective view, in this paper, we focus on individuals’ subjective and asymmetric opinions on their interrelationships. Inspired by the theories from sociolinguistics, we investigate two individuals’ opinions on their interrelationship with their interactive language features. Eliminating the difference of personal language style, we clarify that the asymmetry of interactive language feature values can indicate individuals’ asymmetric opinions on their interrelationship. We also discuss how the degree of opinions’ asymmetry is related to the individuals’ personality traits. Furthermore, to measure the individuals’ asymmetric opinions on interrelationship concretely, we develop a novel model synthetizing interactive language and social network features. The experimental results with Enron email dataset provide multiple evidences of the asymmetric opinions on interrelationship, and also verify the effectiveness of the proposed model in measuring the degree of opinions’ asymmetry.
📄 Content
Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features Bo Wang Tianjin University Yanshu Yu Tianjin University Yuan Wang Tianjin University
ABSTRACT
Instead of studying the properties of social relationship from an
objective view, in this paper, we focus on individuals’ subjective
and asymmetric opinions on their interrelationships. Inspired by
the theories from sociolinguistics, we investigate two individuals’
opinions on their interrelationship with their interactive language
features. Eliminating the difference of personal language style, we
clarify that the asymmetry of interactive language feature values
can
indicate
individuals’
asymmetric
opinions on
their
interrelationship. We also discuss how the degree of opinions’
asymmetry is related to the individual’s personality traits.
Furthermore, to measure the individuals’ asymmetric opinions on
interrelationship concretely, we develop a novel model
synthetizing interactive language and social network features. The
experimental results with Enron email dataset provide multiple
evidences of the asymmetric opinions on interrelationship, and
also verify the effectiveness of the proposed model in measuring
the degree of opinions’ asymmetry.
CCS Concepts
• Human-centered computing ➝ Collaborative and social
computing ➝ Collaborative and social computing design and
evaluation methods ➝ Social network analysis.
Keywords
Social Interrelationship; Social Network, Interactive Language;
Asymmetric Opinions
- INTRODUCTION
The main problem that we are attempting to investigate in this
paper is the following: given a pair of individuals who are
engaged in discourse, are their subjective opinions of their
interrelationship symmetric or not, and how can we measure their
subjective opinions on their interrelationship?
To recognize the nature of interrelationships between individuals
is a very essential problem in social computing, which is the basis
of many related studies such as community discovery, influence
analysis, link predication and recommendation [3]. Actually,
when we try to determine the nature of an interrelationship, we
have two primary options: The first one is regarding the nature of
interrelationships as objective properties, which can be
investigated independently of the participants’ subjective opinions.
The second option is to determine the nature of interrelationships
according to two participants’ subjective opinions on their
interrelationships. In practice, the objective measurement often
leads to symmetric values of the interrelationships’ properties,
while the subjective measurement can leads to asymmetric values,
because two participants may have different opinions on their
interrelationship. The verification and measurement of this kind of
subjective asymmetry is important in many social computing
studies, For example, in influence analysis, the information
propagation possibility is not balanced between two individuals:
the one who believes their interrelationship is strong tend to
pass/receive more information, and the other one who believes the
interrelationship is weak will do the opposite.
Generally speaking, the important problems of the subjective measurement of interrelationship should include: (1) Can we verify the intuition about the opinions’ asymmetry on social interrelationship with experimental evidence? (2) How to measure the asymmetric opinions on interrelationship? (3) Does the degree of the subjective asymmetry of the interrelationship has any latent reasons, e.g., the personality traits of the participant individuals?
To answer these questions, the key is to find a more direct method to investigate the individuals’ subjective opinions on their interrelationship. In this work, we propose to do this with the features from interactive language between individuals. In section 3.2, according to related theories in sociolinguistics, we select four typical interactive language features which indicate the frequency, quantity, quality and emotion of interactive language, respectively. In section 3.3 we further normalize these linguistic features with each individual’s preference of language using to distinguish the personal opinions from the personal language habit. In section 4, we propose an optimization process to measure the individuals’ asymmetric opinions of their interrelationship with their interactive language features. The experiments in section 5 investigate the asymmetry of individuals’ opinions on interrelationship with multiple experimental evidences. The experiments in section 6 verify the effectiveness of the proposed measurement of the asymmetric opinions on interrelationship. - RELATED WORK 2.1 Symmetric & Asymmetric Analysis of Signed Social Interrelationships Many early studies of the social relationship suppose the properties of interrelationships are symmetric. Am
This content is AI-processed based on ArXiv data.