04.Data collection03.Mechanical Turk - sporedata/researchdesigneR GitHub Wiki

1. Use cases: in which situations should I use this method?

  • Labeling of simple medical images
  • Labeling simple medical text
  • Surveys about common conditions in the general population

2. Input: what kind of data does the method require?

  1. If the study requires that respondents have a specific condition or characteristic, then this condition or characteristic should be fairly common.
  2. The study does not require identifiers

3. Algorithm: how does the method work?

Model mechanics

The Mechanical Turk is a now traditional data collection site coordinated by amazon.com where individuals -- called Turks -- from all over the world register to answer questionnaires and then get paid for their answers. Some studies have shown that responses obtained through Mechanical Turk can generate results that are fairly representative of the US population while others have shown differences (see Self-reported Health Status Differs for Amazon's Mechanical Turk Respondents Compared With Nationally Representative Surveys, although those results will depend on the specific population being studied. The Mechanical Turk is frequently used for randomized trials.

Reporting guidelines for Methods

  • Tapped out or barely tapped? Recommendations for how to harness the vast and largely unused potential of the Mechanical Turk participant pool [1].

Systems Perspective of Amazon Mechanical Turk for Organizational Research: Review and Recommendations

Data science packages

Suggested companion methods

  • Trial is the design of choice
  • Surveys if a survey is the design of choice
  • Discrete choice modeling
  • Qualitative methods and text analytics if there are open questions

Learning materials

  1. Books *
  2. Articles *
  3. SporeData-specific

References

[1] Robinson J, Rosenzweig C, Moss AJ, Litman L. Tapped out or barely tapped? Recommendations for how to harness the vast and largely unused potential of the Mechanical Turk participant pool. PloS one. 2019 Dec 16;14(12):e0226394.

⚠️ **GitHub.com Fallback** ⚠️