From Task Classification Towards Similarity Measures for Recommendation in Crowdsourcing Systems
This work provides a foundation for improving recommender systems in crowdsourcing to help individuals find appropriate tasks, but it appears incremental as it builds on prior findings about semantic aspects.
The paper tackled the problem of task selection in micro-task markets by developing similarity measures for recommendation, showing that automatic classification of tasks based on descriptions is possible and proposing measures to cluster tasks by semantic aspects.
Task selection in micro-task markets can be supported by recommender systems to help individuals to find appropriate tasks. Previous work showed that for the selection process of a micro-task the semantic aspects, such as the required action and the comprehensibility, are rated more important than factual aspects, such as the payment or the required completion time. This work gives a foundation to create such similarity measures. Therefore, we show that an automatic classification based on task descriptions is possible. Additionally, we propose similarity measures to cluster micro-tasks according to semantic aspects.