A myriad of emerging applications from simple to complex ones involve human cognizance in the computation loop. Using the wisdom of human workers, researchers have solved a variety of problems, termed as “micro-tasks” such as, captcha recognition, sentiment analysis, image categorization, query processing, as well as “complex tasks” that are often collaborative, such as, classifying craters on planetary surfaces, discovering new galaxies (Galaxyzoo), performing text translation. The current view of “humans-in-the-loop” tends to see humans as machines, robots, or low-level agents used or exploited in the service of broader computation goals. This dissertation is developed to shift the focus back to humans, and study different data analytics problems, by recognizing characteristics of the human workers, and how to incorporate those in a principled fashion inside the computation loop.
The first contribution of this dissertation is to propose an optimization framework and a real world system to personalize worker’s behavior by developing a worker model and using that to better understand and estimate task completion time. The framework judiciously frames questions and solicits worker feedback on those to update the worker model. Next, improving workers skills through peer interaction during collaborative task completion is studied. A suite of optimization problems are identified in that context considering collaborativeness between the members as it plays a major role in peer learning. Finally, “diversified” sequence of work sessions for human workers is designed to improve worker satisfaction and engagement while completing tasks.
|
![[NJIT logo]](http://archives.njit.edu/vhlib/images/njit_logo.gif){kind=logo}
![[Van Houten Library logo]](images/vhl-top-image.jpg)
