Books et al.Research Methods

Social science, today

See allHide authors and affiliations

Science  05 Jan 2018:
Vol. 359, Issue 6371, pp. 42
DOI: 10.1126/science.aaq0679

eLetters is an online forum for ongoing peer review. Submission of eLetters are open to all. eLetters are not edited, proofread, or indexed.  Please read our Terms of Service before submitting your own eLetter.

Compose eLetter

Plain text

  • Plain text
    No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Author Information
First or given name, e.g. 'Peter'.
Your last, or family, name, e.g. 'MacMoody'.
Your email address, e.g. higgs-boson@gmail.com
Your role and/or occupation, e.g. 'Orthopedic Surgeon'.
Your organization or institution (if applicable), e.g. 'Royal Free Hospital'.
Statement of Competing Interests
CAPTCHA

This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

Image CAPTCHA
Enter the characters shown in the image.

Vertical Tabs

  • Automatically building a formula by machine learning using big data for social science

    David Lazer wrote an article entitled "Social Science, today" (1). Many of social science researchers have been currently formulating parameters of collected data with expert knowledge. If the formulated equation manually by researchers is a reasonable, it may be able to produce the rational result. However, more complex system with a large number of parameters cannot be modeled by researchers. Machine learning technologies allows us to automatically build a model of the relationship between complicated parameters using big data. In other words, manually formulating parameters by researchers is not needed anymore. Machine learning technologies include ensemble machine learning based on statistics ( Adaboost, Random Forest, Extra Tree, Extra Trees, Gradient Boosting, Bagging, Voting) and deep learning. Deep learning system can be built by deep learning frameworks. Google uses Tensorflow and Keras frameworks, Amazon Mxnet and Gluon frameworks, Microsoft CNTK framework , Facebook Pytorch and Caffe2 frameworks respectively. Now, researchers can build a target system using open source deep learning frameworks and/or open source ensemble machine learning APIs.

    References:
    1. David Lazer, "Social Science, today," Science 5 Jan 2018, VOL 359 ISSUE 6371, p.42

    Competing Interests: None declared.