Speaker: Hilla Shinitzky
Title: Improving collective decision aggregation through cognitive and meta-cognitive features engineering
The outcome of a collective's tasks and decision-making process, such as when using crowdsourcing, often relies heavily on the procedure through which the dispersed perspectives of individuals are aggregated. There are various aggregation techniques, most of which come down to a simple and sometimes effective deterministic aggregation rule (e.g., the Majority rule). Some methods also try to exploit meta-cognitive data, such as the confidence of individual group members in their solution. However, there are still a significant number of cases in which a trustworthy solution is difficult to achieve.
This research investigates the possibility of exploiting and learning from the cognitive and meta-cognitive information itself, using Machine-Learning (ML) techniques. Ultimately, based on this core idea, several different approaches for aggregating a final collective decision, including a novel meta-aggregation method, are proposed. Contrary to other ML-based aggregation techniques, these methods have the advantage of being independent of the crowd-specific composition and personal record and adaptive to various types of situations.
Hilla Shinitzky is a PhD student in the Department of Software and Information Systems Engineering at Ben-Gurion University of the Negev, under the advisement of Prof. Yuval Shahar. She received both her MSc and BSc in Information Systems Engineering at Ben-Gurion University. Her research interests include data science, collective intelligence, and human computation.