Abstract

This paper aims at modeling and inferring the influence among individuals from voting data (or more generally from actions that are selected by choosing one of m different options). The voting data are modeled as outcomes of a discrete random process, that we refer to as the discuss-then-vote model, whose evolution is governed by the DeGroot opinion dynamics with stubborn nodes. Based on the proposed model, we formulate the maximum-a-posterior estimator for the opinions and influence matrix (or the transition matrix) and derive a tractable approximation that results in a convex optimization problem. In the paper, the identifiability of the network dynamics' parameters and the vote prediction procedure based on the influence matrix, are discussed in depth. Our methodology is tested through numerical simulations as well as through its application to a set of the United States Senate roll call data. Interestingly, in spite of the relatively small data record available, the influence matrix inferred from the real data is consistent with the common intuition about the influence structure in the US Senate.

Original languageEnglish (US)
JournalIEEE Transactions on Signal Processing
DOIs
StateAccepted/In press - Apr 26 2018

Fingerprint

Dynamic models
Convex optimization
Random processes
Computer simulation

Keywords

  • Analytical models
  • Data mining
  • Data mining
  • Data models
  • influence analysis
  • Linear matrix inequalities
  • Senator
  • Signal processing
  • social network
  • Social network services
  • Steady-state
  • US government

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Estimating Social Opinion Dynamics Models from Voting Records. / Wu, Xiaoxiao; Wai, Hoi To; Scaglione, Anna.

In: IEEE Transactions on Signal Processing, 26.04.2018.

Research output: Contribution to journalArticle

@article{fd9428313d5946bb87628aa2fe9b6f04,
title = "Estimating Social Opinion Dynamics Models from Voting Records",
abstract = "This paper aims at modeling and inferring the influence among individuals from voting data (or more generally from actions that are selected by choosing one of m different options). The voting data are modeled as outcomes of a discrete random process, that we refer to as the discuss-then-vote model, whose evolution is governed by the DeGroot opinion dynamics with stubborn nodes. Based on the proposed model, we formulate the maximum-a-posterior estimator for the opinions and influence matrix (or the transition matrix) and derive a tractable approximation that results in a convex optimization problem. In the paper, the identifiability of the network dynamics' parameters and the vote prediction procedure based on the influence matrix, are discussed in depth. Our methodology is tested through numerical simulations as well as through its application to a set of the United States Senate roll call data. Interestingly, in spite of the relatively small data record available, the influence matrix inferred from the real data is consistent with the common intuition about the influence structure in the US Senate.",
keywords = "Analytical models, Data mining, Data mining, Data models, influence analysis, Linear matrix inequalities, Senator, Signal processing, social network, Social network services, Steady-state, US government",
author = "Xiaoxiao Wu and Wai, {Hoi To} and Anna Scaglione",
year = "2018",
month = "4",
day = "26",
doi = "10.1109/TSP.2018.2827321",
language = "English (US)",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Estimating Social Opinion Dynamics Models from Voting Records

AU - Wu, Xiaoxiao

AU - Wai, Hoi To

AU - Scaglione, Anna

PY - 2018/4/26

Y1 - 2018/4/26

N2 - This paper aims at modeling and inferring the influence among individuals from voting data (or more generally from actions that are selected by choosing one of m different options). The voting data are modeled as outcomes of a discrete random process, that we refer to as the discuss-then-vote model, whose evolution is governed by the DeGroot opinion dynamics with stubborn nodes. Based on the proposed model, we formulate the maximum-a-posterior estimator for the opinions and influence matrix (or the transition matrix) and derive a tractable approximation that results in a convex optimization problem. In the paper, the identifiability of the network dynamics' parameters and the vote prediction procedure based on the influence matrix, are discussed in depth. Our methodology is tested through numerical simulations as well as through its application to a set of the United States Senate roll call data. Interestingly, in spite of the relatively small data record available, the influence matrix inferred from the real data is consistent with the common intuition about the influence structure in the US Senate.

AB - This paper aims at modeling and inferring the influence among individuals from voting data (or more generally from actions that are selected by choosing one of m different options). The voting data are modeled as outcomes of a discrete random process, that we refer to as the discuss-then-vote model, whose evolution is governed by the DeGroot opinion dynamics with stubborn nodes. Based on the proposed model, we formulate the maximum-a-posterior estimator for the opinions and influence matrix (or the transition matrix) and derive a tractable approximation that results in a convex optimization problem. In the paper, the identifiability of the network dynamics' parameters and the vote prediction procedure based on the influence matrix, are discussed in depth. Our methodology is tested through numerical simulations as well as through its application to a set of the United States Senate roll call data. Interestingly, in spite of the relatively small data record available, the influence matrix inferred from the real data is consistent with the common intuition about the influence structure in the US Senate.

KW - Analytical models

KW - Data mining

KW - Data mining

KW - Data models

KW - influence analysis

KW - Linear matrix inequalities

KW - Senator

KW - Signal processing

KW - social network

KW - Social network services

KW - Steady-state

KW - US government

UR - http://www.scopus.com/inward/record.url?scp=85046361711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046361711&partnerID=8YFLogxK

U2 - 10.1109/TSP.2018.2827321

DO - 10.1109/TSP.2018.2827321

M3 - Article

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

ER -