Increasing the veracity of event detection on social media networks through user trust modeling

Bodnar, Todd; Tucker, Conrad S.; Hopkinson, Kenneth M.; Bilén, Sven G.

doi:10.1109/bigdata.2014.7004286

Cited by 37 publications

(26 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors have demonstrated that large-scale social media networks exhibit the five Vs of "big data" and can serve as a viable source of real-time knowledge extraction though data mining [16,17].…”

Section: Big Data Frameworkmentioning

confidence: 99%

Data-Throughput Enhancement Using Data Mining-Informed Cognitive Radio

et al. 2015

Self Cite

View full text Add to dashboard Cite

We propose the data mining-informed cognitive radio, which uses non-traditional data sources and data-mining techniques for decision making and improving the performance of a wireless network. To date, the application of information other than wireless channel data in cognitive radios has not been significantly studied. We use a novel dataset (Twitter traffic) as an indicator of network load in a wireless channel. Using this dataset, we present and test a series of predictive algorithms that show an improvement in wireless channel utilization over traditional collision-detection algorithms. Our results demonstrate the viability of using these novel datasets to inform and create more efficient cognitive radio networks.

show abstract

Section: Big Data Frameworkmentioning

confidence: 99%

Data-Throughput Enhancement Using Data Mining-Informed Cognitive Radio

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data veracity is becoming a research hotspot of big data and there have been many related studies in the literature [2,4,10,16,20,15]. For example, Kepner et al [10] introduced a new technique called Computing on Masked Data (CMD) to improve data veracity while allowing a wide range of computations and queries to be performed with low overhead by combining efficient cryptographic encryption methods with an associative array representation of big data.…”

Section: Related Workmentioning

confidence: 99%

“…For example, Kepner et al [10] introduced a new technique called Computing on Masked Data (CMD) to improve data veracity while allowing a wide range of computations and queries to be performed with low overhead by combining efficient cryptographic encryption methods with an associative array representation of big data. Bodnar et al [4] proposed a veracity assessment model for information dissemination on social media networks that combines natural language processing and machine learning algorithms to mine textual content generated by each user. Sanger et al [20] introduced two veracity research branches emerging from the combination of the terms of interest, namely Big Data for Trust and Trust in Big Data.…”

Section: Related Workmentioning

confidence: 99%

Toward better data veracity in mobile cloud computing: A context-aware and incentive-based reputation mechanism

Lin

Tian

et al. 2017

Information Sciences

View full text Add to dashboard Cite

Abstract:As a promising next-generation computing paradigm, Mobile Cloud Computing (MCC) enables the large-scale collection and big data processing of personal private data. An important but often overlooked V of big data is data veracity, which ensures that the data used are trusted, authentic, accurate and protected from unauthorized access and modification. In order to realize the veracity of data in MCC, specific trust models and approaches must be developed. In this paper, a Category-based Context-aware and Recommendation incentive-based reputation Mechanism (CCRM) is proposed to defend against internal attacks and enhance data veracity in MCC. In the CCRM, innovative methods, including a data category and context sensing technology, a security relevance evaluation model, and a Vickrey-Clark-Groves (VCG)-based recommendation incentive scheme, are integrated into the process of reputation evaluation. Cost analysis indicates that the CCRM has a linear communication and computation complexity. Simulation results demonstrate the superior performance of the CCRM compared to existing reputation mechanisms under internal collusion attacks and bad mouthing attacks.

show abstract

“…The U.S. Outpatient Influenza-like Illness Surveillance Network (ILINet) collects information on patient visits to health care providers for influenza-like illness in all 50 states, Puerto Rico, the District of Columbia and the U.S. Virgin Islands, reporting more than 30 million patient visits each year [27]. ILINet provides information through the Centers for Disease Control and Prevention (CDC) 5 , in the form of weekly influenza infection rates across all the geographical regions in the United States.…”

Section: Cutting-edge Solutions For Disease Detectionmentioning

confidence: 99%

“…Online communities generate more than 2.5 quintillion (10 18 ) bytes of data each day [42,5]. A large portion of this data is generated through social media services such as Twitter, Facebook, and Google Plus that process anywhere between 12 terabytes (10 12 ) to 20 petabytes (10 15 ) of data each day [1].…”

Section: Introductionmentioning

confidence: 99%

Modeling Individual-Level Infection Dynamics Using Social Network Information

Tuarob

Tucker

Salathé

et al. 2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Epidemic monitoring systems engaged in accurate discovery of infected individuals enable better understanding of the dynamics of epidemics and thus may promote effective disease mitigation or prevention. Currently, infection discovery systems require either physical participation of potential patients or provision of information from hospitals and health-care services. While social media has emerged as an increasingly important knowledge source that reflects multiple real world events, there is only a small literature examining how social media information can be incorporated into computational epidemic models. In this paper, we demonstrate how social media information can be incorporated into and improve upon traditional techniques used to model the dynamics of infectious diseases. Using flu infection histories and social network data collected from 264 students in a college community, we identify social network signals that can aid identification of infected individuals. Extending the traditional SIRS model, we introduce and illustrate the efficacy of an Online-Interaction-Aware SusceptibleInfected-Recovered-Susceptible (OIA-SIRS) model based on four social network signals for modeling infection dynamics. Empirical evaluations of our case study, flu infection within a college community, reveal that the OIA-SIRS model is more accurate than the traditional model, and also closely tracks the real-world infection rates as reported by CDC ILINet and Google Flu Trend.

show abstract

Increasing the veracity of event detection on social media networks through user trust modeling

Cited by 37 publications

References 38 publications

Data-Throughput Enhancement Using Data Mining-Informed Cognitive Radio

Data-Throughput Enhancement Using Data Mining-Informed Cognitive Radio

Toward better data veracity in mobile cloud computing: A context-aware and incentive-based reputation mechanism

Modeling Individual-Level Infection Dynamics Using Social Network Information

Contact Info

Product

Resources

About