한국노동연구원 전자도서관

로그인

한국노동연구원 전자도서관

자료검색

  1. 메인
  2. 자료검색
  3. 신착자료 검색

신착자료 검색

단행본

Bit by bit: social research in the digital age

청구기호
300.72 BIT2018
발행사항
Princeton, New Jersey : Princeton University Press, 2018
형태사항
423 p
서지주기
Includes bibliographical references and index
ISBN
9780691158648
소장정보
위치등록번호청구기호 / 출력상태반납예정일
이용 가능 (1)
한국노동연구원00009135대출가능-
이용 가능 (1)
  • 등록번호
    00009135
    상태/반납예정일
    대출가능
    -
    위치/청구기호(출력)
    한국노동연구원
책 소개

An innovative and accessible guide to doing social research in the digital age

In just the past several years, we have witnessed the birth and rapid spread of social media, mobile phones, and numerous other digital marvels. In addition to changing how we live, these tools enable us to collect and process data about human behavior on a scale never before imaginable, offering entirely new approaches to core questions about social behavior. Bit by Bit is the key to unlocking these powerful methods?a landmark book that will fundamentally change how the next generation of social scientists and data scientists explores the world around us.

Bit by Bit is the essential guide to mastering the key principles of doing social research in this fast-evolving digital age. In this comprehensive yet accessible book, Matthew Salganik explains how the digital revolution is transforming how social scientists observe behavior, ask questions, run experiments, and engage in mass collaborations. He provides a wealth of real-world examples throughout and also lays out a principles-based approach to handling ethical challenges.

Bit by Bit is an invaluable resource for social scientists who want to harness the research potential of big data and a must-read for data scientists interested in applying the lessons of social science to tomorrow’s technologies.

  • Illustrates important ideas with examples of outstanding research
  • Combines ideas from social science and data science in an accessible style and without jargon
  • Goes beyond the analysis of “found” data to discuss the collection of “designed” data such as surveys, experiments, and mass collaboration
  • Features an entire chapter on ethics
  • Includes extensive suggestions for further reading and activities for the classroom or self-study


목차
1 Preface 2 Introduction 2.1 Reader note 2.2 Outline of the book 3 Observing 3.1 Introduction 3.2 Found data vs designed data 3.3 Common characteristics of digital exhaust 3.3.1 Good characteristics 3.3.1.1 Big 3.3.1.2 Always-on 3.3.1.3 Non-reactive 3.3.2 Bad properties 3.3.2.1 Incomplete 3.3.2.2 Corporate 3.3.2.3 Non-representative 3.3.2.4 Drifting 3.3.2.5 Algorithmic confounding 3.3.2.6 Spammy 3.3.3 Conclusion 3.4 Research strategies 3.4.1 Counting things 3.4.1.1 Taxis in New York City 3.4.1.2 Friendship formation among students 3.4.1.3 Censorship of social media by the Chinese government 3.4.1.4 Conclusion 3.4.2 Forecasting and nowcasting 3.4.2.1 Forecasting 3.4.2.2 Nowcasting 3.4.3 Approximately experiments 3.4.3.1 Natural experiments 3.4.3.2 Matching 3.5 Conclusion 3.6 Further reading 3.7 Activities 4 Asking 4.1 Introduction 4.2 Asking vs. observing 4.3 The total survey error framework 4.3.1 Representation 4.3.2 Measurement 4.3.3 Cost 4.4 Who to ask 4.4.1 Probability sampling: data collection and data analysis 4.4.2 Data analysis for non-probability samples 4.4.2.1 Xbox panel to predict the US election 4.4.3 Data collection in non-probability samples: sample matching 4.4.4 Conclusion 4.5 New ways of asking questions 4.5.1 Ecological momentary assessments 4.5.2 Wiki surveys 4.5.3 Gamification 4.6 Surveys linked to other data 4.6.1 Amplified asking 4.6.1.1 Wealth and well-being in Rwanda 4.6.2 Enriched asking 4.6.2.1 Who votes? 4.7 Conclusion 4.8 Technical appendix: Mathematical approach to probability and non-probability samples 4.9 Further reading 4.10 Activities 5 Experiments 5.1 Introduction 5.2 What are experiments? 5.3 Lab experiments, field experiments, and digital experiments 5.4 From evaluation to understanding and optimization 5.4.1 Validity 5.4.2 Heterogeneity of treatment effects 5.4.3 Mechanisms 5.5 Four types of experiments 5.5.1 Embedded experiments 5.5.1.1 Emotional contagion 5.5.1.2 Get out the vote 5.5.1.3 General properties of embedded experiments 5.5.2 Overlaid experiments 5.5.2.1 The visible hand and measuring discrimination 5.5.2.2 Cumulative advantage in social systems 5.5.2.3 General properties of overlaid experiments 5.5.3 Experiments in online labor markets 5.5.3.1 Can democracy work? 5.5.3.2 The cost of annoying ads 5.5.3.3 General properties of experiments on online labor markets 5.5.4 Group experiments 5.5.4.1 MusicLab 5.5.4.2 The spread of behavior in networks 5.5.4.3 General properties of group experiments 5.6 Conclusion 5.7 Technical appendix: Potential outcomes framework 5.8 Further reading 5.9 Activities 6 Collaborating 6.1 Introduction 6.2 Human computation 6.2.1 Galaxy Zoo 6.2.2 Crowd-coding of political manifestos 6.2.3 Conclusion 6.3 Open calls 6.3.1 Netflix Prize 6.3.2 Foldit 6.3.3 Peer-to-Patent 6.3.4 Conclusion 6.4 Distributed data collection 6.4.1 eBird 6.4.2 PhotoCity 6.4.3 Conclusion 6.5 Designing your own 6.5.1 Motivate participants 6.5.2 Leverage heterogeneity 6.5.3 Focus attention 6.5.4 Enable surprise 6.5.5 Be ethical 6.5.6 Final design advice 6.6 Conclusion 6.7 Further reading 6.8 Activities 7 Ethics 7.1 Introduction 7.2 Research ethics in the analog age 7.2.1 Historic atrocities 7.2.2 Belmont Report 7.2.3 The Common Rule and IRBs 7.3 Research ethics in the digital age 7.3.1 Three examples 7.3.1.1 Emotional Contagion 7.3.1.2 Taste, Ties, and Time 7.3.1.3 Encore 7.3.2 Digital is different 7.3.3 Menlo Report 7.4 Foundational ideas 7.4.1 Principles 7.4.1.1 Respect for Persons 7.4.1.2 Beneficence 7.4.1.3 Justice 7.4.1.4 Respect for Law and Public Interest 7.4.2 Ethical frameworks 7.5 Areas of difficulty 7.5.1 Informed consent 7.5.1.1 Experiments without consent to study discrimination 7.5.1.2 Some form of consent for most research 7.5.1.3 Informed consent in practice 7.5.2 Understanding and managing informational risk 7.5.2.1 “Anonymization” and de-anonymization 7.5.2.2 Managing information risk 7.5.2.3 Information risk and sharing research data 7.5.3 Making decisions in the face of uncertainty 7.5.3.1 Minimal risk standard 7.5.3.2 Power analysis 7.5.3.3 Ethical-response surveys 7.5.3.4 Staged trials 7.6 Practical tips 7.6.1 The IRB is a floor, not a ceiling 7.6.2 Put yourself in everyone else’s shoes 7.6.3 Think of research ethics as continuous, not discrete 7.7 Conclusion 7.8 Further reading 7.9 Activities 8 Future