"Subjective Well-Being and Social Media shows how, by exploiting the unprecedented amount of information provided by the social networking sites, it is possible to build new composite indicators of subjective well-being. These new social media indicators are complementary to official statistics and surveys, whose data are collected at very low temporary and geographical resolution. The book also explains in full details how to solve the problem of selection bias coming from social media data. Mixing textual analysis, machine learning and time series analysis, the book also shows how to extract both the structural and the temporary components of subjective well-being. Cross-country analysis confirms that well-being is a complex phenomenon that is governed by macroeconomic and health factors, ageing, temporary shocks and cultural and psychological aspects. As an example, the last part of the book focuses on the impact of the prolonged stress due to the COVID-19 pandemic on subjective well-being in both Japan and Italy. Through a data science approach, the results show that a consistent and persistent drop occurred throughout 2020 in the overall level of well-being in both countries. The methodology presented in this book: enables social scientists and policy makers to know what people think about the quality of their own life, minimizing the bias induced by the interaction between the researcher and the observed individuals; being language-free, it allows for comparing the well-being perceived in different linguistic and socio-cultural contexts, disentangling differences due to objective events and life conditions from dissimilarities related to social norms or language specificities; provides a solution to the problem of selection bias in social media data through a systematic approach based on time-space small area estimation models. The book comes also with replication R scripts and data. Stefano M. Iacus is full professor of Statistics at the University of Milan, on leave at the Joint Research Centre of the European Commission. Former R-core member (1999-2017) and R Foundation Member. Giuseppe Porro is full professor of Economic Policy at the University of Insubria. An earlier version of this project was awarded the Italian Institute of Statistics-Google prize for "official statistics and big data""-- Provided by publisher

nexusstc/Subjective Well-Being and Social Media/0e5ec7bb62bcc6b72df29006f1c3ba6b.pdf

lgli/Subjective_Well-Being_and_Social_Media.pdf

lgrsnf/Subjective_Well-Being_and_Social_Media.pdf

zlib/Mathematics/Stefano M Iacus; Giuseppe Porro/Subjective Well-Being and Social Media_17680515.pdf

Subjective Well-Being and Social Networks

Iacus, Stefano M., Porro, Giuseppe

STEFANO M.. PORRO, GIUSEPPE IACUS

Ashgate Publishing Limited

Chapman and Hall/CRC

Taylor & Francis Ltd

Gower Publishing Ltd

CRC Press LLC

A Chapman & Hall Book, First edition, Boca Raton London New York, 2021

United Kingdom and Ireland, United Kingdom

First edition, Boca Raton, FL, 2021

First edition, Boca Raton, 2022

Boca Raton ; Abingdon, 2021

1, 2021

Mobilism

sources:
9780429401435

producers:
Acrobat Pro DC 20.13.20074

{"isbns":["0429401434","1032043164","1138393924","9780429401435","9781032043166","9781138393929"],"last_page":218,"publisher":"CRC Press"}

The authors describe a social media index for measuring subjective well-being, relying on the availability of big data sources provided by the social networking sites, and on one of the most recent techniques for sentiment analysis. This approach disentangles the main methodological issues raised in the literature on well-being measurement.
Cover 1
Half Title 2
Title Page 4
Copyright Page 5
Dedication 6
Contents 8
Preface 12
1. Subjective and Social Well-Being 16
1.1. Introduction 16
1.1.1. Subjective Well-Being 16
1.1.2. Objective Measures 17
1.1.3. Multidimensional Indicators 18
1.1.4. Surveys 19
1.1.5. Social Networking Sites and Data at Scale 19
1.1.6. What You’ll Find (and What You’ll Not) in This Book 21
1.1.7. Wellbeing, Well Being or Well-Being? 22
1.2. Gross Domestic Product 22
1.3. Well-Being as a Multidimensional Notion 26
1.3.1. The Capability Approach 26
1.3.1.1. Empirical Limitations of the Capability Approach 27
1.3.2. Multidimensional Well-Being Indicators 28
1.3.2.1. HDI: Human Development Index 29
1.3.2.2. BLI: Better Life Index 29
1.3.2.3. HPI: Happy Planet Index 30
1.3.2.4. BES: Benessere Equo Sostenibile (Fair Sustainable Well-Being) 30
1.3.2.5. CIW: Canadian Index of Well-Being 31
1.3.2.6. Other Initiatives for Measuring Well-Being 31
1.3.2.7. GNH: Gross National Happiness 32
1.3.2.8. Pros and Cons of Multidimensional Indicators 33
1.4. Self-Reported Well-Being 34
1.4.1. Gallup Surveys 34
1.4.1.1. Gallup World Poll 34
1.4.1.2. Gallup-Sharecare and Global Well-Being Index 36
1.4.1.3. Well-Being Research Based on Gallup Data 37
1.4.2. European Social Survey 38
1.4.3. World Values Survey 41
1.4.4. European Quality of Life Survey 41
1.4.5. How to Collect (and Interpret) Self-Reported Evaluations 42
1.5. Social Networking Sites and Well-Being 45
1.5.1. Sentiment Analysis 46
1.5.2. Evaluating Subjective Well-Being on the Web 47
1.5.3. Pros and Cons of Large-Scale Data from SNS 55
1.5.4. International and Intercultural Comparisons 58
1.6. Subjective or Social Well-Being? 59
1.7. Glossary 60
2. Text and Sentiment Analysis 62
2.1. Text Analysis 62
2.1.1. Main Principles of Text Analysis 63
2.2. Different Types of Estimation and Targets 65
2.3. From Texts to Numbers: How Computers Crunch Documents 66
2.3.1. Modeling the Data Coming for Social Networks 69
2.4. Review of Unsupervised Methods 70
2.4.1. Scoring Methods: Wordfish, Wordscores and LLS 70
2.4.2. Continuous Space Word Representation: Word2Vec 73
2.4.3. Cluster Analysis 76
2.4.4. Topic Models 77
2.5. Review of Machine Learning Methods 80
2.5.1. Decision Trees and Random Forests 81
2.5.2. Support Vector Machines 84
2.5.3. Artificial Neural Networks 88
2.6. Estimation of Aggregated Distribution 91
2.6.1. The Need of Aggregated Estimation: Reversing the Point of View 92
2.6.2. The ReadMe Solution to the Inverse Problem 94
2.7. The iSA Algorithm 94
2.7.1. Main Advantages of iSA over the ReadMe Approach 95
2.8. The iSAX Algorithm for Sequential Sampling 95
2.9. Empirical Comparison of Machine Learning Methods 96
2.9.1. Confidence Intervals 102
2.10. Conclusions 104
2.11. Glossary 104
3. Extracting Subjective Well-Being from Textual Data 106
3.1. From SNS Data to Subjective Well-Being Indexes 106
3.1.1. Pros & Cons of Twitter Data 106
3.2. The Hedonometer 108
3.3. The Gross National Happiness Index 109
3.4. The World Well-Being Project 110
3.5. The Twitter Subjective Well-Being Index 111
3.5.1. Qualitative Analysis of Texts 113
3.5.2. Data Filtering for Training-Set Construction 114
3.5.3. General Coding Rules 114
3.5.4. Specific Coding Rules 114
3.5.5. How to Construct the Index 120
3.5.6. The Data Collection 121
3.5.7. Some Cultural Elements of SNS Communication in Japan 122
3.6. Preliminary Analysis of the SWB-I & SWB-J Indexes 123
3.7. Cross-Country Analysis 2015–2018 with Structural Equation Modeling 126
3.7.1. Interpretation of the Structural Equation Model 127
3.8. Glossary 131
4. How to Control for Bias in Social Media 134
4.1. Representativeness and Selection Bias of Social Media 134
4.2. Small Area Estimation Method 136
4.2.1. Weighting Strategy 138
4.2.2. The Space-Time SAE Model with Weights 138
4.3. An Application to the Study of Well-Being at Work 140
4.3.1. Data and Variables 140
4.3.2. The Construction of the Weights 141
4.3.3. Official Statistics to Anchor the Model 142
4.3.4. Results of the SAE Model 145
4.3.5. A Weighted Measure of Well-Being at Work 146
4.3.6. The Estimated Measure of Well-Being at Work from the SAE Model 148
4.3.7. Comparison with Official Statistics 151
4.4. Conclusions 153
4.5. Glossary 153
5. Subjective Well-Being and the COVID-19 Pandemic 154
5.1. The Year 2020 and Well-Being 154
5.2. The Effect of Lockdown on Gross National Happiness Index 155
5.3. Hedonometer and the COVID-19 Pandemic 158
5.4. The World Well-Being Project and Tracking of Symptoms During the Pandemic 158
5.5. The Decline of SWB-I & SWB-J During COVID-19 160
5.5.1. Related Studies 164
5.6. Data Collection of Potential Determinants of the SBW Indexes 164
5.6.1. COVID-19 Spread Data 165
5.6.2. Financial Data 165
5.6.3. Air Quality Data 165
5.6.4. Google Search Data 165
5.6.5. Google Mobility Data 167
5.6.6. Facebook Survey Data 167
5.6.7. Restriction Measures Data 167
5.7. What Impacted the Subjective Well-Being Indexes? 168
5.7.1. Preliminary Correlation Analysis 169
5.7.2. Monthly Regression Analysis 169
5.7.3. Dynamic Elastic Net Analysis 176
5.7.4. Analysis of the Italian Data 178
5.7.5. Analysis of the Japanese Data 183
5.7.6. Comparative Analysis of the Dynamic Elastic Net Results 184
5.8. Structural Equation Modeling 185
5.8.1. Evidence from the Structural Equation Modeling 187
5.9. Summary of the Results 191
5.10. Conclusions 193
5.11. Glossary 194
Bibliography 196
Index 220
Subjective,Well-being;,Sentiment,analysis;,Selection,bias,in,social,media;,Twitter,analysis;,Official,statistics,and,big,data;,Welfare,measurement
Subjective Well-being,Sentiment analysis,Selection bias in social media,Twitter analysis,Official statistics and big data,Welfare measurement

2021-10-22