Your browser doesn't support javascript.
A Time-Series-Based New Behavior Trace Model for Crowd Workers That Ensures Quality Annotation.
Al-Qershi, Fattoh; Al-Qurishi, Muhammad; Aksoy, Mehmet Sabih; Faisal, Mohammed; Algabri, Mohammed.
  • Al-Qershi F; Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
  • Al-Qurishi M; College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
  • Aksoy MS; Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
  • Faisal M; College of Applied Computer Sciences, King Saud University, Riyadh 145111, Saudi Arabia.
  • Algabri M; Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
Sensors (Basel) ; 21(15)2021 Jul 23.
Article in English | MEDLINE | ID: covidwho-1346525
ABSTRACT
Crowdsourcing is a new mode of value creation in which organizations leverage numerous Internet users to accomplish tasks. However, because these workers have different backgrounds and intentions, crowdsourcing suffers from quality concerns. In the literature, tracing the behavior of workers is preferred over other methodologies such as consensus methods and gold standard approaches. This paper proposes two novel models based on workers' behavior for task classification. These models newly benefit from time-series features and characteristics. The first model uses multiple time-series features with a machine learning classifier. The second model converts time series into images using the recurrent characteristic and applies a convolutional neural network classifier. The proposed models surpass the current state of-the-art baselines in terms of performance. In terms of accuracy, our feature-based model achieved 83.8%, whereas our convolutional neural network model achieved 76.6%.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Neural Networks, Computer / Crowdsourcing Type of study: Experimental Studies Limits: Humans Language: English Year: 2021 Document Type: Article Affiliation country: S21155007

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Neural Networks, Computer / Crowdsourcing Type of study: Experimental Studies Limits: Humans Language: English Year: 2021 Document Type: Article Affiliation country: S21155007