Syllabus

[chengjun]

如果9月份不补录成绩，7月3日就是deadline；

如果9月份有补录成绩，8月25日就是deadline；

教学大纲

1. 计算社会科学简介
2. 计算社会科学的编程工具（上）
3. 计算社会科学的编程工具（下）
4. 大数据的特征
5. 大数据的研究策略
6. 数字时代的调查
7. 数字时代的实验
8. 学生选题介绍
9. 机器学习简介
10. 机器学习基础
11. 机器学习进阶
12. 文本挖掘（上）
13. 文本挖掘（下）
14. 网络科学（上）
15. 网络科学（下）
16. 社会科学写作（上）
17. 社会科学写作（下）
18. 学生选题展示

1 计算社会科学简介

• Matthew J. Salganik (2017) Bit by Bit_ social research in the digital age. Princeton university press
• Should social science be more solution-oriented?
• Watts (2007) A twenty-first century science. Nature 445.Feb
• Watts (2016) Common sense
• Lazer et al (2009) Compuational social science. Science
• Lessons and Challenges in Computational Social Science
• King, G. (2011). Ensuring the Data-Rich Future of the Social Sciences. Science

homework day 1 mobirise + republic 5 分

2 大数据

• Chetty The Fading American Dream- Trends in Absolute Income Mobility Since 1940
• Wu 2019 Small Team Disrupt
• Ginsberg (2009) Detecting influenza epidemics using google search engine query data. Nature
• Blumenstock 2015 Predicting poverty and wealth frommobile phone metadata

homework day 2 big data5 分

3 休息

• 规模：复杂世界的简单法则

4 调查&实验

• Bond et al (2012) A 61-million-person experiment insocial influence and political mobilization. Nature
• Salganik (2006) Experimental study of inequality andunpredictability in an artificial cultural market. Science
• Phan & Airoldi (2015) A natural experiment of socialnetwork formation and dynamics. PNAS
• Centola (2010) The spread of behavior in an online socialnetwork experiment. Science
• Kramer et al. (2014) Emotional Contagion

homework day 4 survey + experiment 5 分

5 网络科学

• Barabasi Network Science book
• The spread of true and false news online
• Watts 1998 Collective Dynamics of “Small-world” Networks
• Barabasi (1999) Emergence of scaling in randomnetworks. Science. 509-12
• Schich (2014) A network framework of cultural history. Science. 558-62
• Watts (2002) A simple model of global cascade on randomnetworks. PNAS
• Granovetter (1978) Threshold models of collective behavior.AJS
• Granovetter (1973)The strength of weakties. AJS

homework day 5 network true-and-false-news 5 分

6 机器学习入门

• Python Data Science Handbook Essential Tools forWorking with Data by Jake VanderPlas
• Lazer et al. (2014) The parable of Google Flu Traps in bigdata analysis
• Ginsberg (2009) Detecting influenza epidemics using search engine query data. Nature. v457. 19Feb.07634
• Risi (2019) Predicting history
• Salganik (2020) Measuring the predictability of lifeoutcomes with a scientific mass collaboration. PNAS

homework day 6 machine learning googleflu 5 分

7 机器学习算法

• Blumenstock (2015) Predicting poverty and wealth frommobile phone metadata
• Frey & Osborne (2017). The future ofemployment How susceptible are jobs to computerisation.Technological forecasting and social change

homework day 7 machine learning future work & fake newsdetection & poverty prediction5 分

8 神经网络模型

• Dive into Deep Leaning-en-pytorch
• Temporal Fusion Transformers for interpretable multi-horizon time series forecasting

homework day 8 deep learning fake news detection & imagenet vgg16 pretrained model 5 分

9 词向量嵌入模型

• Mikolov (2013) Efficient Estimation of WordRepresentations in Vector Space
• Mikolov (2013) Distributed Representations of Words andPhrases and their Compositionality
• Kozlowski, Taddy & Evans (2019). TheGeometry of Culture Analyzing the Meanings of Class through Word Embeddings. American Sociological Review
• Word embeddings quantify 100 years of gender andethnic stereotypes
• how quantifying the shapes of the stories predict their sucess
• The Cinderella Complex
• node2vec-kdd16
• Perozzi, Al-Rfou, R., & Skiena, S. (2014). DeepWalk. Proceedings of the 20th ACM SIGKDD

homework day 9 embeddings5 分

10 自然语言处理

• Michel (2011) Quantitative analysis of culture usingmillions of digitized books. Science
• Storywrangler: A massive exploratorium for sociolinguistic,cultural, socioeconomic, and political timelines using Twitter