Humans are the ultimate intelligent systems. Units of human work can be used to address the problems studied in the fields of pattern recognition and artificial intelligence. After years of research to crack certain tough problems, mere utterance of the phrase "human cycle" makes it seem like someone turned on a light in the room. Suddenly, we feel we are no longer feeling our way forward in darkness as we develop solutions. Instead, a bright world of new possibilities has been opened.
The excitement that crowdsourcing has generated in computer science is
related to the fact that large crowdsourcing platforms make it possible
to apply abstraction to human input to the system. It is not necessary
to consider who exactly provides the input, or how they "compute" it,
rather the human processor can be treated as a black box. The magic comes
when it is possible to make a "call the the crowd" and be sure that
there will be a crowdworker there to return a value in response to that
However, crowdsourcing raises a whole new array of issues. At the same time that we excitedly pursue the potential of "Artifical artificial intelligence" (as it's called by MTurk), it is necessary to also remember "Human human computation".
I am not an ethicist, and my first foray into crowdsourcing ethics was relatively recent and necessarily superficial. In fact, I started by typing the word "ethics" into my favorite mainstream search engine and picking a definition to study that seemed to me to be authoritative. However, I am convinced that the community of crowdworkers and taskaskers together form an ecosystem and that the main threat to this ecosystem is that we treat it irresponsibly.
In other words, we should not throw out everything that we have learned over centuries of human civilization about creating healthy and happy societies, stable economies and safe and fulfilled individuals in our quest to create new systems. Ultimately, these systems must serve humanity as a whole, and not disproportionately or detrimentally lean on the portion of the population that serves as crowdworkers.
Because of this conviction, I have put together a set of slides about responsible crowdsourcing that serve as notes on the ethical aspects of crowdsourcing. At a recent Dagstuhl seminar entitled, "Crowdsourcing: From Theory to Practice and Long-Term Perspectives" I used the slides to make a presentation intended to serve as a basis for opening a discussion on the ethical issues of crowdsourcing.
The hopeful part of this undertaking is that it revealed many solutions to address ethical aspects of crowdsourcing. Some of them pose challenges that are just as exciting as the ones that motivated us to turn to crowdsourcing in the first place.
Please see the references in the slides, and also these links:
How many Mechanical Turk workers are there?
2 months ago