Milestone 3 TuringMachine DarkHorseIdea: Social Network for Crowdsourcing

From crowdresearch
Revision as of 05:37, 12 July 2015 by Avrimmit (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search


Neil Gaikwad

Leaderboard, social Network for crowdsourcing

Leveraging social network community structure for ensuring Reward, Respect, and Recognition .

Background and Motivation

Based on brainstorming and analysis of various missing components in the existing crowdsourcing system, we draw our design from the social network theory. We propose a crowdsourcing system architecture surrounded by Artificial Intelligence and Machine Learning algorithms. Below diagram gives abstract overview of interactions between various human-human, machine-machine, and human-machine workflows. Furthermore, we zoom into a dark horse specific component of the system i.e . Leaderboard.


The Future of Work, Kittur etal 2013 and Genomes of Collective Intelligence Framework, Malone etal 2010 have shown that Reputation, Incentives, and Motivation play a big role in developing sustainable crowd sourcing communities. However, the question remains how do we motivate people for a long period of time and how do we build the trust? HCI research provides guidelines for developing sustainable online communities. In Building Successful Online Communities: Evidence-Based Social Design, Tausczik, Dabbish, and Kraut 2012 discuss the Identity and bond Based attachments.


Leaderboard profile for Requestors (individual profile as well as group ranking)

  • How might we increase the reputation of requestors?
  • Motivate Requestors to be transparent and attract quality workers.
  • Workers can vote for top requestors who are providing clear instructions about the tasks and fairness. Borda Count Voting algorithm can be implanted to design the system; see Networks, Crowds, and Markets: Reasoning about a Highly Connected World, Kleinberg
  • Create Requestors' profile highlighting their track-records. Make an announcement of top performers.
  • Workers can trust the requestors who are high ranked and provide good value for their time
  • Requestors' reputation will help them attract new talent for accomplishing complex tasks
  • Requestors' reputation will them earn reward from the crowdsourcing system administrators
  • How might we increase the reputation of workers?
  • Motivate workers by being recognized in the community
  • Provide incentive to reach to top using hierarchy

  • Provide value to their commitment and ability to get things done
  • Requestors can trust the worker's profile based on making payments or recruiting them