Utilizing computational trust to identify rumor spreaders on Twitter

Bhavtosh Rath, Wei Gao, Jing Ma, Jaideep Srivastava

Research output: Contribution to journalArticle

Abstract

Ubiquitous use of social media such as microblogging platforms opens unprecedented chances for false information to diffuse online. Facing the challenges in such a so-called “post-fact” era, it is very important for intelligent systems to not only check the veracity of information but also verify the authenticity of the users who spread the information, especially in time-critical situations such as real-world emergencies, where urgent measures have to be taken for stopping the spread of fake information. In this work, we propose a novel machine-learning-based approach for automatic identification of the users who spread rumorous information on Twitter by leveraging computational trust measures, in particular the concept of Believability. We define believability as a measure for assessing the extent to which the propagated information is likely being perceived as truthful or not based on the proxies of trust such as user’s retweet and reply behaviors in the network. We hypothesize that the believability between two users is proportional to the trustingness of the retweeter/replier and the trustworthiness of the tweeter, which are complementary to one another for representing user trust and can be inferred from trust proxies using a variant of HITS algorithm. With the trust network edge-weighted by believability scores, we apply network representation learning algorithms to generate user embeddings, which are then used to classify users into rumor spreaders or not based on recurrent neural networks (RNN). Experimented on a large real-world rumor dataset collected from Twitter, it is demonstrated that our proposed RNN-based method can effectively identify rumor spreaders and outperform four more straightforward, non-RNN models with large margin.

Original languageEnglish
Article number64
JournalSocial Network Analysis and Mining
Volume8
Issue number1
DOIs
Publication statusPublished - 1 Dec 2018
Externally publishedYes

Fingerprint

Spreaders
rumor
Recurrent neural networks
twitter
Intelligent systems
Learning algorithms
Learning systems
Identification (control systems)
neural network
Neural networks
trustworthiness
social media
authenticity
learning

Keywords

  • Computational trust
  • Recurrent neural networks
  • Representation learning
  • Rumor detection

ASJC Scopus subject areas

  • Information Systems
  • Communication
  • Media Technology
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Utilizing computational trust to identify rumor spreaders on Twitter. / Rath, Bhavtosh; Gao, Wei; Ma, Jing; Srivastava, Jaideep.

In: Social Network Analysis and Mining, Vol. 8, No. 1, 64, 01.12.2018.

Research output: Contribution to journalArticle

@article{e36d67867008487d87bff5a3f9175a44,
title = "Utilizing computational trust to identify rumor spreaders on Twitter",
abstract = "Ubiquitous use of social media such as microblogging platforms opens unprecedented chances for false information to diffuse online. Facing the challenges in such a so-called “post-fact” era, it is very important for intelligent systems to not only check the veracity of information but also verify the authenticity of the users who spread the information, especially in time-critical situations such as real-world emergencies, where urgent measures have to be taken for stopping the spread of fake information. In this work, we propose a novel machine-learning-based approach for automatic identification of the users who spread rumorous information on Twitter by leveraging computational trust measures, in particular the concept of Believability. We define believability as a measure for assessing the extent to which the propagated information is likely being perceived as truthful or not based on the proxies of trust such as user’s retweet and reply behaviors in the network. We hypothesize that the believability between two users is proportional to the trustingness of the retweeter/replier and the trustworthiness of the tweeter, which are complementary to one another for representing user trust and can be inferred from trust proxies using a variant of HITS algorithm. With the trust network edge-weighted by believability scores, we apply network representation learning algorithms to generate user embeddings, which are then used to classify users into rumor spreaders or not based on recurrent neural networks (RNN). Experimented on a large real-world rumor dataset collected from Twitter, it is demonstrated that our proposed RNN-based method can effectively identify rumor spreaders and outperform four more straightforward, non-RNN models with large margin.",
keywords = "Computational trust, Recurrent neural networks, Representation learning, Rumor detection",
author = "Bhavtosh Rath and Wei Gao and Jing Ma and Jaideep Srivastava",
year = "2018",
month = "12",
day = "1",
doi = "10.1007/s13278-018-0540-z",
language = "English",
volume = "8",
journal = "Social Network Analysis and Mining",
issn = "1869-5450",
publisher = "Springer Wien",
number = "1",

}

TY - JOUR

T1 - Utilizing computational trust to identify rumor spreaders on Twitter

AU - Rath, Bhavtosh

AU - Gao, Wei

AU - Ma, Jing

AU - Srivastava, Jaideep

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Ubiquitous use of social media such as microblogging platforms opens unprecedented chances for false information to diffuse online. Facing the challenges in such a so-called “post-fact” era, it is very important for intelligent systems to not only check the veracity of information but also verify the authenticity of the users who spread the information, especially in time-critical situations such as real-world emergencies, where urgent measures have to be taken for stopping the spread of fake information. In this work, we propose a novel machine-learning-based approach for automatic identification of the users who spread rumorous information on Twitter by leveraging computational trust measures, in particular the concept of Believability. We define believability as a measure for assessing the extent to which the propagated information is likely being perceived as truthful or not based on the proxies of trust such as user’s retweet and reply behaviors in the network. We hypothesize that the believability between two users is proportional to the trustingness of the retweeter/replier and the trustworthiness of the tweeter, which are complementary to one another for representing user trust and can be inferred from trust proxies using a variant of HITS algorithm. With the trust network edge-weighted by believability scores, we apply network representation learning algorithms to generate user embeddings, which are then used to classify users into rumor spreaders or not based on recurrent neural networks (RNN). Experimented on a large real-world rumor dataset collected from Twitter, it is demonstrated that our proposed RNN-based method can effectively identify rumor spreaders and outperform four more straightforward, non-RNN models with large margin.

AB - Ubiquitous use of social media such as microblogging platforms opens unprecedented chances for false information to diffuse online. Facing the challenges in such a so-called “post-fact” era, it is very important for intelligent systems to not only check the veracity of information but also verify the authenticity of the users who spread the information, especially in time-critical situations such as real-world emergencies, where urgent measures have to be taken for stopping the spread of fake information. In this work, we propose a novel machine-learning-based approach for automatic identification of the users who spread rumorous information on Twitter by leveraging computational trust measures, in particular the concept of Believability. We define believability as a measure for assessing the extent to which the propagated information is likely being perceived as truthful or not based on the proxies of trust such as user’s retweet and reply behaviors in the network. We hypothesize that the believability between two users is proportional to the trustingness of the retweeter/replier and the trustworthiness of the tweeter, which are complementary to one another for representing user trust and can be inferred from trust proxies using a variant of HITS algorithm. With the trust network edge-weighted by believability scores, we apply network representation learning algorithms to generate user embeddings, which are then used to classify users into rumor spreaders or not based on recurrent neural networks (RNN). Experimented on a large real-world rumor dataset collected from Twitter, it is demonstrated that our proposed RNN-based method can effectively identify rumor spreaders and outperform four more straightforward, non-RNN models with large margin.

KW - Computational trust

KW - Recurrent neural networks

KW - Representation learning

KW - Rumor detection

UR - http://www.scopus.com/inward/record.url?scp=85056110676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056110676&partnerID=8YFLogxK

U2 - 10.1007/s13278-018-0540-z

DO - 10.1007/s13278-018-0540-z

M3 - Article

VL - 8

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

SN - 1869-5450

IS - 1

M1 - 64

ER -