Task Personalization for Inexpertise Workers in Incentive Based Crowdsourcing Platforms

Crowdsourcing is an emerging technology which enables human workers to perform the task that cannot be done using automated tools. The crucial constituent of crowdsourcing platform is human workers. Since crowdsourcing platforms are overcrowded, workers find difficulty in selecting a suitable task for them. Employing task recommendation systems could improve this situation. However, task recommendation for new and inexpert workers is not explored well. We address this problem by designing a task recommendation model using skill taxonomy and participation probability of existing expert workers. The proposed model is validated through experimentation with both real and synthetic dataset.