Advanced search
1 file | 699.85 KB

Identifying and properly handling context in crowdsourcing

(2018) APPLIED SOFT COMPUTING. 73. p.203-214
Author
Organization
Abstract
Using proper social media content in decision making is an ongoing challenge for modern information management. Since such content could be highly subjective, diverse and, thus, hard to process by computer-based algorithms, its truthfulness and suitability are increasingly assessed by people through crowdsourcing services. However, crowdsourced assessments can also be highly subjective. In this paper, we propose a novel method to obtain an approximation of the level to which the contexts of subjective (fuzzy) judgments on social media content are perceived as alike, thereby providing a tool to identify, measure and handle context in crowdsourcing. To compute such an approximation, the proposed method takes two augmented (Atanassov) intuitionistic fuzzy sets (AAIFSs) as input, each characterizing the appraisals that a respondent makes on a specific collection of social media posts. The approximation is based on the AAIFS elements corresponding to the appraisals of a specific number of posts, which are deemed to be well fitted (or unfitted) specimens of the concept under analysis. We demonstrate that simulated appraisals support the effectiveness of the proposed method.
Keywords
Crowdsourcing, Semantic richer comparison, Experience-based evaluation, Crowdsourced (fuzzy) data, Subjective information

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 699.85 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Loor Romero, Marcelo Eduardo, and Guy De Tré. 2018. “Identifying and Properly Handling Context in Crowdsourcing.” Applied Soft Computing 73: 203–214.
APA
Loor Romero, M. E., & De Tré, G. (2018). Identifying and properly handling context in crowdsourcing. APPLIED SOFT COMPUTING, 73, 203–214.
Vancouver
1.
Loor Romero ME, De Tré G. Identifying and properly handling context in crowdsourcing. APPLIED SOFT COMPUTING. Elsevier BV; 2018;73:203–14.
MLA
Loor Romero, Marcelo Eduardo, and Guy De Tré. “Identifying and Properly Handling Context in Crowdsourcing.” APPLIED SOFT COMPUTING 73 (2018): 203–214. Print.
@article{8574780,
  abstract     = {Using proper social media content in decision making is an ongoing challenge for modern information management. Since such content could be highly subjective, diverse and, thus, hard to process by computer-based algorithms, its truthfulness and suitability are increasingly assessed by people through crowdsourcing services. However, crowdsourced assessments can also be highly subjective. In this paper, we propose a novel method to obtain an approximation of the level to which the contexts of subjective (fuzzy) judgments on social media content are perceived as alike, thereby providing a tool to identify, measure and handle context in crowdsourcing. To compute such an approximation, the proposed method takes two augmented (Atanassov) intuitionistic fuzzy sets (AAIFSs) as input, each characterizing the appraisals that a respondent makes on a specific collection of social media posts. The approximation is based on the AAIFS elements corresponding to the appraisals of a specific number of posts, which are deemed to be well fitted (or unfitted) specimens of the concept under analysis. We demonstrate that simulated appraisals support the effectiveness of the proposed method.},
  author       = {Loor Romero, Marcelo Eduardo and De Tré, Guy},
  issn         = {1568-4946},
  journal      = {APPLIED SOFT COMPUTING},
  keywords     = {Crowdsourcing,Semantic richer comparison,Experience-based evaluation,Crowdsourced (fuzzy) data,Subjective information},
  language     = {eng},
  pages        = {203--214},
  publisher    = {Elsevier BV},
  title        = {Identifying and properly handling context in crowdsourcing},
  url          = {http://dx.doi.org/10.1016/j.asoc.2018.04.062},
  volume       = {73},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: