Papers in CSS

CSS: Computational Social Science

Contributed by Huimin Chen, Cheng Yang, Xuanming Zhang and Yun Shi.

Introduction

Computational Social Science (CSS) is a fast-emerging field, striving to address socical science problems with the assistance of computational methods. This repo contains the list of all relavant papers surveyed in our paper From Symbols to Embeddings: A Tale of Two Representations in Computational Social Science. Specifically, the structure of this paperlist is organized as three parts: Table of Content for Text, Table of Content for Network and Table of Content for Research Domains.

Note that we established the paperlist by investigating on more than 400 top-cited articles from 6 representative publications over ten years. These publications include three prestigious multidisciplinary academic journals, namely Nature, Science and PNAS, and three top conferences in computer science strongly related to CSS, namely ACL, WWW and KDD.

Corrections and suggestions are welcomed!

Table of Content for Text

1. Symbol-based representation
1.1 Word	1.1.1 Frequency-based
	1.1.2 Feature-based
	1.1.3 Network-based
1.2 Sentence	1.2.1 Frequency-based
	1.2.2 Feature-based
2. Embedding-based representation
2.1 Word	2.1.1 Word Embeding-based
2.2 Sentence	2.2.1 Topic Model-based
	2.2.2 Neural-based

Table of Content for Network

1. Symbol-based representation
1.1 Node	1.1.1 Node & Edge-based Statistics
	1.1.2 Centrality-based
	1.1.3 Designed Index
	1.1.4 Probablistic Model
1.2 Subgraph	1.2.1 Motif-based statistics/coefficients/index
	1.2.2 Cluster-based statistics/coefficients/index
2. Embedding-based representation
2.1 Node & Subgraph	2.1.1 Matrix Factorization
	2.1.2 Neural-based

Table of Content for Research Domains

1. Sociology	2. Anthropology
3. Psychology	4. Politics
5. Economics	6. Linguistics
7. Communication	8. Geography
9. Environment

Text

Symbol-based representation

Word

Frequency-based

1. Ontogeny and phylogeny of language. PNAS 110.16 (2013). paper

   Charles Yang.

2. Quantitative analysis of culture using millions of digitized books. Science 331.6014 (2011). paper

   Jean-Baptiste Michel et al.

3. Aspirational pursuit of mates in online dating markets. Science Advances 4.8 (2018). paper

   Elizabeth E Bruch and MEJ Newman.

4. What does Congress want from the National Science Foundation? A content analysis of remarks from 1995 to 2018. Science Advances 6.33 (2020). paper

   A Lupia, S Soroka, and A Beatty.

5. The public and legislative impact of hyperconcentrated topic news. Science Advances 5.8 (2019). paper

   Karthik Sheshadri and Munindar P Singh.

6. Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures. Science 333.6051 (2011). paper

   Scott A Golder and Michael W Macy.

7. Quantifying the relationship between financial news and the stock market. Scientific Reports 3.1 (2013). paper

   Merve Alanyali, Helen Susannah Moat, and Tobias Preis.

Feature-based

1. Human language reveals a universal positivity bias. PNAS 112.8 (2015). paper

   Peter Sheridan Dodds et al.

2. Natural speech reveals the semantic maps that tile human cerebral cortex. Nature 532.7600 (2016). paper

   Alexander G Huth et al.

Network-based

1. Bots increase exposure to negative and inflammatory content in online social systems. PNAS 115.49 (2018). paper

   Massimo Stella, Emilio Ferrara, and Manlio De Domenico.

2. Algorithms in the historical emergence of word senses. PNAS 115.10 (2018). paper

   Christian Ramiro et al.

3. Emotion semantics show both cultural variation and universal structure. Science 366.6472 (2019). paper

   Joshua Conrad Jackson et al.

4. Lexical shifts, substantive changes, and continuity in State of the Union discourse, 1790–2014. PNAS 112.35 (2015). paper

   Alix Rule, Jean-Philippe Cointet, and Peter S Bearman.

5. Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. Scientific Reports 8.1 (2018). paper

   Alexandre Bovet, Flaviano Morone, and Herna ́n A Makse.

Sentence

Frequency-based

1. Patterns of text reuse in a scientific corpus. PNAS 112.1 (2015). paper

   Daniel T Citron and Paul Ginsparg.

2. Facebook language predicts depression in medical records. PNAS 115.44 (2018). paper

   Johannes C Eichstaedt et al.

3. Elusive consensus: Polarization in elite communication on the COVID-19 pandemic. Science Advances 6.28 (2020). paper

   Jon Green et al.

4. Exposure to ideologically diverse news and opinion on Facebook. Science 348.6239 (2015). paper

   Eytan Bakshy, Solomon Messing, and Lada A Adamic.

5. Word lengths are optimized for efficient communication. PNAS 108.9 (2011). paper

   Steven T Piantadosi, Harry Tily, and Edward Gibson.

Feature-based

1. Large-scale evidence of dependency length minimization in 37 languages. PNAS 112.33 (2015). paper

   Richard Futrell, Kyle Mahowald, and Edward Gibson.

2. Examining long-term trends in politics and culture through language of political leaders and cultural institutions. PNAS 116.9 (2019). paper

   Kayla N Jordan et al.

3. Happiness and the patterns of life: A study of geolocated tweets. Scientific Reports 3.1 (2013). paper

   Morgan R Frank et al.

4. Rapid assessment of disaster damage using social media activity. Science Advances 2.3 (2016). paper

   Yury Kryvasheyeu et al.

5. The civilizing process in London’s Old Bailey. PNAS 111.26 (2014). paper

   Sara Klingenstein, Tim Hitchcock, and Simon DeDeo.

6. The incidence and role of negative citations in science. PNAS 112.45 (2015). paper

   Christian Catalini, Nicola Lacetera, and Alexander Oettl.

7. The narrative arc: Revealing core narrative structures through text analysis. Science Advances 6.32 (2020). paper

   Ryan L Boyd, Kate G Blackburn, and James W Pennebaker.

8. Quantitative patterns of stylistic influence in the evolution of literature. PNAS 109.20 (2012). paper

   James M Hughes et al.

9. Experimental evidence of massive-scale emotional contagion through social networks. PNAS 111.24 (2014). paper

   Adam DI Kramer, Jamie E Guillory, and Jeffrey T Hancock.

10. Emotion shapes the diffusion of moralized content in social networks. PNAS 114.28 (2017). paper

    William J Brady et al.

11. Distress and rumor exposure on social media during a campus lockdown. PNAS 114.44 (2017). paper

    Nickolas M Jones et al.

12. Bots increase exposure to negative and inflammatory content in online social systems. PNAS 115.49 (2018). paper

    Massimo Stella, Emilio Ferrara, and Manlio De Domenico.

13. Echo chambers: Emotional contagion and group polarization on facebook. Scientific Reports 6.1 (2016). paper

    Michela Del Vicario et al.

14. Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. Scientific Reports 8.1 (2018). paper

    Alexandre Bovet, Flaviano Morone, and Herna ́n A Makse.

15. Content-based features predict social media influence operations. Science Advances 6.30 (2020). paper

    Meysam Alizadeh et al.

16. What does Congress want from the National Science Foundation? A content analysis of remarks from 1995 to 2018. Science Advances 6.33 (2020). paper

    A Lupia, S Soroka, and A Beatty.

Embedding-based representation

Word

Word Embedding-based

1. Word embeddings quantify 100 years of gender and ethnic stereotypes. PNAS 115.16 (2018). paper

   Nikhil Garg et al.

2. Semantics derived automatically from language corpora contain human-like biases. Science 356.6334 (2017). paper

   Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan.

3. Parents mention sons more often than daughters on social media. PNAS 116.6 (2019). paper

   Elizaveta Sivak and Ivan Smirnov.

Sentence

Topic Model-based

1. Measuring discursive influence across scholarship. PNAS 115.13 (2018). paper

   Aaron Gerow et al.

2. What does Congress want from the National Science Foundation? A content analysis of remarks from 1995 to 2018. Science Advances 6.33 (2020). paper

   A Lupia, S Soroka, and A Beatty.

3. Race, religion and the city: twitter word frequency patterns reveal dominant demographic dimensions in the United States. Palgrave Communications 2.1 (2016). paper

   Eszter Boka ́nyi et al.

4. Network structure and influence of the climate change counter-movement. Nature Climate Change 6.4 (2016). paper

   Justin Farrell.

5. Predicting the birth of a spoken word. PNAS 112.41 (2015). paper

   Brandon C Roy et al.

6. Quantifying the semantics of search behavior before stock market moves. PNAS 111.32 (2014). paper

   C. Curme et al.

7. Corporate funding and ideological polarization about climate change. PNAS 113.1 (2016). paper

   Justin Farrell.

8. Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods. PNAS 117.19 (2020). paper

   Kokil Jaidka et al.

9. Facebook language predicts depression in medical records. PNAS 115.44 (2018). paper

   Johannes C Eichstaedt et al.

Neural-based

1. The public and legislative impact of hyperconcentrated topic news. Science Advances 5.8 (2019). paper

   Karthik Sheshadri and Munindar P Singh.

2. Restoration of fragmentary Babylonian texts using recurrent neural networks. PNAS 117.37 (2020). paper

   Ethan Fetaya et al.

3. Universals of word order reflect optimization of grammars for efficient communication. PNAS 117.5 (2020). paper

   Michael Hahn, Dan Jurafsky, and Richard Futrell.

4. Moralization in social networks and the emergence of violence during protests. Nature Human Behaviour 2.6 (2018). paper

   Marlon Mooijman et al.

Network

Symbol-based representation

Node

Node & Edge-based Statistics

1. Fake news on Twitter during the 2016 US presidential election. Science 363.6425 (2019). paper

   Nir Grinberg et al.

2. A comparative analysis of the statistical properties of large mobile phone calling networks. Scientific Reports 4.1 (2014). paper

   Ming-Xia Li et al.

3. A psychological intervention strengthens students’ peer social networks and promotes persistence in STEM. Science Advances 6.45 (2020). paper

   Kate M Turetsky et al.

4. Social networks and cooperation in hunter-gatherers. Nature 481.7382 (2012). paper

   Coren L Apicella et al.

5. How social and genetic factors predict friendship networks. PNAS 109.43 (2012). paper

   Jason D Boardman, Benjamin W Domingue, and Jason M Fletcher.

6. Systematic inequality and hierarchy in faculty hiring networks. Science Advances 1.1 (2015). paper

   Aaron Clauset, Samuel Arbesman, and Daniel B Larremore.

7. Document co- citation analysis to enhance transdisciplinary research. Science Advances 4.1 (2018). paper

   Caleb M Trujillo and Tammy M Long.

8. Quantifying the impact of human mobility on malaria. Science 338.6104 (2012). paper

   Amy Wesolowski et al.

9. Spatial patterns of close relationships across the lifespan. Scientific Reports 4.1 (2014). paper

   Hang-Hyun Jo et al.

10. Similar neural responses predict friendship. Nature Communications 9.1 (2018). paper

    Carolyn Parkinson, Adam M Kleinbaum, and Thalia Wheatley.

11. Large teams develop and small teams disrupt science and technology. Nature 566.7744 (2019). paper

    Lingfei Wu, Dashun Wang, and James A Evans.

12. The strength of long-range ties in population- scale social networks. Science 362.6421 (2018). paper

    Patrick S Park, Joshua E Blumenstock, and Michael W Macy.

13. Leaking privacy and shadow profiles in online social networks. Science Advances 3.8 (2017). paper

    David Garcia.

Centrality-based

1. A psychological intervention strengthens students’ peer social networks and promotes persistence in STEM. Science Advances 6.45 (2020). paper

   Kate M Turetsky et al.

2. A network framework of cultural history. Science 345.6196 (2014). paper

   Maximilian Schich et al.

3. Women’s connectivity in extreme networks. Science Advances 2.6 (2016). paper

   Pedro Manrique et al.

4. Networks of global bird invasion altered by regional trade ban. Science Advances 3.11 (2017). paper

   Luıs Reino et al.

5. Effects of population dispersal on regional signaling networks: An example from northern Iroquoia. Science Advances 3.8 (2017). paper

   John P Hart, Jennifer Birch, and Christian Gates St-Pierre.

6. Quantifying reputation and success in art. Science 362.6416 (2018). paper

   Samuel P Fraiberger et al.

7. Aspirational pursuit of mates in online dating markets. Science Advances 4.8 (2018). paper

   Elizabeth E Bruch and MEJ Newman.

8. Searching for superspreaders of information in real-world social media. Scientific Reports 4.1 (2014). paper

   Sen Pei et al.

9. Hiding individuals and communities in a social network. Nature Human Behaviour 2.2 (2018). paper

   Marcin Waniek et al.

Designed Index

1. The dynamics of meaningful social interactions and the emergence of collective knowledge. Scientific Reports 5.1 (2015). paper

   Marija Mitrovic ́ Dankulov, Roderick Melnik, and Bosiljka Tadic ́.

2. Cumulative effects of triadic closure and homophily in social networks. Science Advances 6.19 (2020). paper

   Aili Asikainen et al.

3. Social connections with COVID-19–affected areas increase compliance with mobility restrictions. Science Advances 6.47 (2020). paper

   Ben Charoenwong, Alan Kwan, and Vesa Pursiainen.

4. Identifying influential and susceptible members of social networks. Science 337.6092 (2012). paper

   Sinan Aral and Dylan Walker.

5. Generalized friendship paradox in complex networks: The case of scientific collaboration. Scientific Reports 4.1 (2014). paper

   Young-Ho Eom and Hang-Hyun Jo.

6. Large teams develop and small teams disrupt science and technology. Nature 566.7744 (2019). paper

   Lingfei Wu, Dashun Wang, and James A Evans.

7. Resilience and efficiency in transportation networks. Science Advances 3.12 (2017). paper

   Alexander A Ganin et al.

8. Searching for superspreaders of information in real-world social media. Scientific Reports 4.1 (2014). paper

   Sen Pei et al.

Probablitic Model

1. The dynamics of meaningful social interactions and the emergence of collective knowledge. Scientific Reports 5.1 (2015). paper

   Marija Mitrovic ́ Dankulov, Roderick Melnik, and Bosiljka Tadic ́.

2. Inferring propagation paths for sparsely observed perturbations on complex networks. Science Advances 2.10 (2016). paper

   Francesco Alessandro Massucci et al.

3. Collective influence of multiple spreaders evaluated by tracing real information flow in large-scale social networks. Scientific Reports 6.1 (2016). paper

   Xian Teng et al.

4. Identification and impact of discoverers in online social systems. Scientific Reports 6.1 (2016). paper

   Matu ́ sˇ Medo et al.

Subgraph

Motif-based statistics/coefficients/index

1. Cumulative effects of triadic closure and homophily in social networks. Science Advances 6.19 (2020). paper

   Aili Asikainen et al.

2. Temporal motifs reveal homophily, gender-specific patterns, and group talk in call sequences. PNAS 110.45 (2013). paper

   Lauri Kovanen et al.

Cluster-based statistics/coefficients/index

1. Document co- citation analysis to enhance transdisciplinary research. Science Advances 4.1 (2018). paper

   Caleb M Trujillo and Tammy M Long.

2. Emotion semantics show both cultural variation and universal structure. Science 366.6472 (2019). paper

   Joshua Conrad Jackson et al.

3. Uncovering space-independent communities in spatial networks. PNAS 108.19 (2011). paper

   Paul Expert et al.

4. Hiding individuals and communities in a social network. Nature Human Behaviour 2.2 (2018). paper

   Marcin Waniek et al.

Embedding-based representation

Node & Subgraph

Matrix Factorization

1. Like like alike: joint friendship and interest propagation in social networks. WWW 2011. paper

   Shuang-Hong Yang et al.

2. Using content and interactions for discovering communities in social networks. WWW 2012. paper

   Mrinmaya Sachan et al.

3. Private traits and attributes are predictable from digital records of human behavior. PNAS 110.15 (2013). paper

   Michal Kosinski, David Stillwell, and Thore Graepel.

4. Magnet community identification on social networks. SIGKDD 2012. paper

   Guan Wang et al.

Neural-based

1. Revisiting user mobility and social relationships in lbsns: A hypergraph embedding approach. WWW 2019. paper

   Dingqi Yang et al.

2. Regions, periods, activities: Uncovering urban dynamics via cross-modal representation learning. WWW 2017. paper

   Chao Zhang et al.

3. Graph neural networks for social recommendation. WWW 2019. paper

   Wenqi Fan et al.

4. Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. WWW 2019. paper

   Qitian Wu et al.

Research Domains

Sociology

Symbol-based representation

1. Aspirational pursuit of mates in online dating markets. Science Advance 4.8 (2018). paper

   E.E.Bruch and M.E.J.Newman

2. Bots increase exposure to negative and inflammatory content in online social systems. PNAS 115.49 (2018). paper

   M. Stella, E. Ferrara, and M. De Domenico.

3. Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald trump. Scientific Reports 8.1 (2018). paper

   A. Bovet, F. Morone, and H. A. Maks.

4. Exposure to ideologically diverse news and opinion on Facebook. Science 348.6239 (2015). paper

   E. Bakshy, S. Messing, and L. A. Adamic.

5. Happiness and the patterns of life: A study of Geolocated tweets. Scientific Reports 3.1 (2013). paper

   M. R. Frank et al.

6. The incidence and role of negative citations in science. PNAS 112.45 (2015). paper

   C. Catalini, N. Lacetera, and A. Oettl.

7. Quantitative patterns of stylistic influence in the evolution of literature. PNAS 109.20 (2012). paper

   J. M. Hughes et al.

8. Emotion shapes the diffusion of moralized content in social networks. PNAS 114.28 (2017). paper

   W. J. Brady et al.

9. Distress and rumor exposure on social media during a campus lockdown. PNAS 114.44 (2017). paper

   N. M. Jones et al.

10. Echo chambers: Emotional contagion and group polarization on facebook. Scientific Reports 6.1 (2016). paper

    M. Del Vicario et al.

11. Content-based features predict social media influence operations. Science Advance 6.30 (2020). paper

    M. Alizadeh et al.

12. Systematic inequality and hierarchy in faculty hiring networks. Science Advance 1.1 (2015). paper

    A. Clauset, S. Arbesman, and D. B. Larremore.

Embedding-based representation

Anthropology

Symbol-based representation

1. The civilizing process in London’s Old Bailey. PNAS 111.26 (2014). paper

   Sara Klingenstein, Tim Hitchcock, and Simon DeDeo.

2. Universality and diversity in human song. Science 366.6468 (2019). paper

   Samuel A Mehr et al.

Embedding-based representation

1. Restoration of fragmentary Babylonian texts using recurrent neural networks. PNAS 117.37 (2020). paper

   Ethan Fetaya et al.

2. Happiness and the patterns of life: A study of geolocated tweets. Scientific Reports 3.1 (2013). paper

   Morgan R Frank et al.

Psychology

Symbol-based representation

1. Experimental evidence of massive-scale emotional contagion through social networks. PNAS 111.24 (2014). paper

   Adam DI Kramer, Jamie E Guillory, and Jeffrey T Hancock.

2. Facebook language predicts depression in medical records. PNAS 115.44 (2018). paper

   Johannes C Eichstaedt et al.

3. The grass is greener on the other side: Understanding the effects of green spaces on Twitter user sentiments. WWW 2018. paper

   Kwan Hui Lim et al.

4. Don’t let me be misunderstood: Comparing intentions and perceptions in online discussions. WWW 2020. paper

   Jonathan P Chang, Justin Cheng, and Cristian Danescu- Niculescu-Mizil.

5. Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures. Science 333.6051 (2011). paper

   Scott A Golder and Michael W Macy.

6. Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods. PNAS 117.19 (2020). paper

   Kokil Jaidka et al.

7. What about mood swings: Identifying depression on twitter with temporal measures of emotions. WWW 2018. paper

   Xuetong Chen et al.

Embedding-based representation

1. Facebook language predicts depression in medical records. PNAS 115.44 (2018). paper

   Johannes C Eichstaedt et al.

2. Knowledge-aware assessment of severity of suicide risk for early intervention. WWW 2019. paper

   Manas Gaur et al.

3. Deepmood: modeling mobile phone typing dynamics for mood detection. KDD 2017. paper

   Bokai Cao et al.

4. Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods. PNAS 117.19 (2020). paper

   Kokil Jaidka et al.

5. Moralization in social networks and the emergence of violence during protests. Nature Human Behaviour 2.6 (2018). paper

   Marlon Mooijman et al.

6. Identifying referential intention with heterogeneous contexts. WWW 2020. paper

   Wenhao Yu et al.

7. Social media-predicted personality traits and values can help match people to their ideal jobs. PNAS 116.52 (2019). paper

   Margaret L Kern et al.

Politics

Symbol-based representation

1. What does Congress want from the National Science Foundation? A content analysis of remarks from 1995 to 2018. Science Advances 6.33 (2020). paper

   A Lupia, S Soroka, and A Beatty.

2. Examining long-term trends in politics and culture through language of political leaders and cultural institutions. PNAS 116.9 (2019). paper

   Kayla N Jordan et al.

3. Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. Scientific Reports 8.1 (2018). paper

   Alexandre Bovet, Flaviano Morone, and Herna ́n A Makse.

4. Beyond binary labels: political ideology prediction of twitter users. ACL 2017. paper

   Daniel Preo ̧tiuc-Pietro et al.

5. Content-based features predict social media influence operations. Science Advances 6.30 (2020). paper

   Meysam Alizadeh et al.

6. Collective classification of congressional floor-debate transcripts. ACL 2011. paper

   Clint Burfoot, Steven Bird, and Timothy Baldwin.

7. Lexical shifts, substantive changes, and continuity in State of the Union discourse, 1790–2014. PNAS 112.35 (2015). paper

   Alix Rule, Jean-Philippe Cointet, and Peter S Bearman.

8. Classification of Moral Foundations in Microblog Political Discourse. ACL 2018. paper

   Kristen Johnson and Dan Goldwasser.

9. Leveraging Behavioral and Social Information for Weakly Supervised Collective Classification of Political Discourse on Twitter. ACL 2017. paper

   Kristen Johnson, Di Jin, and Dan Goldwasser.

10. A user-centric model of voting intention from Social Media. ACL 2013. paper

    Vasileios Lampos, Daniel Preotiuc-Pietro, and Trevor Cohn.

11. Learning to Extract International Relations from Political Context. ACL 2013. paper

    Brendan O’Connor, Brandon M. Stewart, and Noah A. Smith.

12. Who falls for online political manipulation? WWW 2019. paper

    Adam Badawy, Kristina Lerman, and Emilio Ferrara.

13. Emotion shapes the diffusion of moralized content in social networks. PNAS 114.28 (2017). paper

    William J Brady et al.

Embedding-based representation

1. Universals of word order reflect optimization of grammars for efficient communication. PNAS 117.5 (2020). paper

   Michael Hahn, Dan Jurafsky, and Richard Futrell.

2. Facebook Ads Monitor: An Independent Auditing System for Political Ads on Facebook. WWW 2020. paper

   Ma ́rcio Silva et al.

3. Predicting the topical stance and political leaning of media using tweets. ACL 2020. paper

   Peter Stefanov et al.

4. Prta: A System to Support the Analysis of Propaganda Techniques in the News. ACL 2020. paper

   Giovanni Da San Martino et al.

5. Encoding social information with graph convolutional networks forpolitical perspective detection in news media. ACL 2019. paper

   Chang Li and Dan Goldwasser.

6. Beyond binary labels: political ideology prediction of twitter users. ACL 2017. paper

   Daniel Preo ̧tiuc-Pietro et al.

7. A Frame of Mind: Using Statistical Models for Detection of Framing and Agenda Setting Campaigns. ACL 2015. paper

   Oren Tsur, Dan Calacci, and David Lazer.

8. Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress. ACL 2015. paper

   Viet-An Nguyen et al.

9. Political Ideology Detection Using Recursive Neural Networks. ACL 2014. paper

   Mohit Iyyer et al.

10. Learning to Extract International Relations from Political Context. ACL 2013. paper

    Brendan O’Connor, Brandon M. Stewart, and Noah A. Smith.

11. What does Congress want from the National Science Foundation? A content analysis of remarks from 1995 to 2018. Science Advances 6.33 (2020). paper

    A Lupia, S Soroka, and A Beatty.

Economics

Symbol-based representation

1. Quantifying the relationship between financial news and the stock market. Scientific Reports 3.1 (2013). paper

   Merve Alanyali, Helen Susannah Moat, and Tobias Preis.

2. Semantic frames to predict stock price movement. ACL 2013. paper

   Boyi Xie et al.

Embedding-based representation

1. Quantifying the semantics of search behavior before stock market moves. PNAS 111.32 (2014). paper

   C. Curme et al.

2. HTML: Hierarchical Transformer- based Multi-task Learning for Volatility Prediction. WWW 2020. paper

   Linyi Yang et al.

3. Stock Movement Prediction from Tweets and Historical Prices. ACL 2018. paper

   Yumo Xu and Shay B. Cohen.

4. Topic modeling based sentiment analysis on social media for stock market prediction. ACL 2015. paper

   Thien Hai Nguyen and Kiyoaki Shirai.

5. Semantic frames to predict stock price movement. ACL 2013. paper

   Boyi Xie et al.

6. Repeat buyer prediction for e- commerce. KDD 2016. paper

   Guimei Liu et al.

7. Predicting socio-economic indicators using news events. KDD 2016. paper

   Sunandan Chakraborty et al.

Linguistics

Symbol-based representation

1. Human language reveals a universal positivity bias. PNAS 112.8 (2015). paper

   Peter Dodds et al.

2. Ontogeny and phylogeny of language. PNAS 110.16 (2013). [paper][https://www.pnas.org/doi/pdf/10.1073/pnas.1216803110]

   Charles Yang

3. Quantitative analysis of culture using millions of digitized books. Science 331.6014 (2011). paper

   Jean-Baptiste Michel et al.

4. Emotion semantics show both cultural variation and universal structure. Science 366.6472 (2019). paper

   Joshua Jackson et al.

5. Word lengths are optimized for efficient communication. PNAS 108.9 (2011). paper

   Steven Piantadosi, Harry Tily, and Edward Gibson

6. Large-scale evidence of dependency length minimization in 37 languages. PNAS 112.33 (2015). paper

   Richard Futrell , Kyle Mahowald, and Edward Gibson

7. Examining long-term trends in politics and culture through language of political leaders and cultural institutions. PNAS 116.9 (2019). paper

   Kayla Jordan et al.

8. The narrative arc: Revealing core narrative structures through text analysis. Science Advances 6.32 (2020). paper

   Ryan Boyd, Kate Blackburn and James Pennebaker

9. Quantitative patterns of stylistic influence in the evolution of literature. PNAS 109.20 (2012). paper

   James Hughes et al.

10. User review sites as a resource for large-scale sociolinguistic studies WWW 2015. paper

    Dirk Hovy et al.

11. A computational approach to politeness with application to social factors ACL 2013. paper

    Cristian Danescu-Niculescu-Mizil et al.

12. You had me at hello: How phrasing affects memorability. ACL 2012. paper

    Cristian Danescu-Niculescu-Mizil et al.

13. The effect of wording on message propagation: Topic- and author- controlled natural experiments on Twitter. ACL 2014. paper

    Chenhao Tan, Lillian Lee and Bo Pang

14. Detecting biased statements in Wikipedia. WWW 2018. paper

    Christoph Hube and Besnik Fetahu

15. Nonliteral understanding of number words. PNAS 111.33 (2014). paper

    Justine Kao et al.

16. On the universal structure of human lexical semantics. PNAS 113.7 (2016). paper

    Hyejin Youn et al.

17. Knowledge gaps in the early growth of semantic feature networks. Nature Human Behavior 2.9 (2018). paper

    Ann Sizemore et al.

18. Links that speak: The global language network and its association with global fame PNAS 111.52 (2014). paper

    Shahar Ronen et al.

Embedding-based representation

1. Natural speech reveals the semantic maps that tile human cerebral cortex. Nature 532.7600 (2016). paper

   Alexander Huth et al.

2. Quantitative patterns of stylistic influence in the evolution of literature. PNAS 109.20 (2012). paper

   James M. Hughes et al.

3. Race, religion and the city: Twitter word frequency patterns reveal dominant demographic dimensions in the United States. Nature Palgrave Communication 2.1 (2016). paper

   Eszter Bokányi et al.

4. Predicting the birth of a spoken word. PNAS 112.41 (2015). paper

   Brandon Roy et al.

5. A robust framework for estimating linguistic alignment in twitter conversations. WWW 2016. paper

   Gabriel Doyle, Dan Yurovsky and Michael Frank

6. Statistically significant detection of linguistic change. WWW 2015. paper

   Vivek Kulkarni et al.

7. Simple, interpretable and stable method for detecting words with usage change across corpora. ACL 2020. paper

   Hila Gonen et al.

Communication

Symbol-based representation

1. Analyzing and predicting viral tweets. WWW 2013. paper

   Maximilian Jenders, Gjergji Kasneci, and Felix Naumann.

2. Opencrowd: A human-ai collaborative approach for finding social influencers via open- ended answers aggregation. WWW 2020. paper

   Ines Arous et al.

3. The public and legislative impact of hyperconcentrated topic news. Science Advances 5.8 (2019). paper

   Karthik Sheshadri and Munindar P Singh.

4. Elusive consensus: Polarization in elite communication on the COVID-19 pandemic. Science Advances 6.28 (2020). paper

   Jon Green et al.

5. Emotion shapes the diffusion of moralized content in social networks. PNAS 114.28 (2017). paper

   William J Brady et al.

Embedding-based representation

1. Topic-level social network search. KDD 2011. paper

   Jie Tang et al.

2. Network structure and influence of the climate change counter-movement. Nature Climate Change 6.4 (2016). paper

   Justin Farrell.

3. The public and legislative impact of hyperconcentrated topic news. Science Advances 5.8 (2019). paper

   Karthik Sheshadri and Munindar P Singh.

4. A Frame of Mind: Using Statistical Models for Detection of Framing and Agenda Setting Campaigns. ACL 2015. paper

   Oren Tsur, Dan Calacci, and David Lazer.

Geography

Symbol-based representation

1. Location inference using microblog messages. WWW 2012. paper

   Yohei Ikawa, Miki Enoki, and Michiaki Tatsubori

2. Inferring twitter user locations with 10 km accuracy. WWW 2014. paper

   KyoungMin Ryoo and Sue Moon.

3. Simple supervised document geolocation with geodesic grids. ACL 2011. paper

   Benjamin Wing and Jason Baldridge.

4. Socroutes: safe routes based on tweet sentiments. WWW 2014. paper

   Jaewoo Kim, Meeyoung Cha, and Thomas Sandholm.

Embedding-based representation

1. Hierarchical geographical modeling of user locations from social media posts. WWW 2013. paper

   Amr Ahmed, Liangjie Hong, and Alexander J Smola.

2. Regions, periods, activities: Uncovering urban dynamics via cross-modal representation learning. WWW 2017. paper

   Chao Zhang et al.

3. Who, where, when and what: discover spatio-temporal topics for twitter users. KDD 2013. paper

   Quan Yuan et al.

4. Travel time estimation of a path using sparse trajectories. KDD 2014. paper

   Yilun Wang, Yu Zheng, and Yexiang Xue.

5. Gmove: Group-level mobility modeling using geo-tagged social media. KDD 2016. paper

   Chao Zhang et al.

6. Triovecevent: Embedding-based online local event detection in geo-tagged tweet streams. KDD 2017. paper

   Chao Zhang et al.

7. Unifying text, metadata, and user network representations with a neural network for geolocation prediction. ACL 2017. paper

   Yasuhide Miura et al.

8. Discovering geographical topics in the twitter stream. WWW 2012. paper

   Liangjie Hong et al.

Environment

Symbol-based representation

1. Rapid assessment of disaster damage using social media activity. Science Advances 2.3 (2016). paper

   Yury Kryvasheyeu et al.

2. Class specific TF-IDF boosting for short-text classification: Application to short-texts generated during disasters. WWW 2018. paper

   Samujjwal Ghosh and Maunendra Sankar Desarkar.

Embedding-based representation

1. Network structure and influence of the climate change counter-movement. Nature Climate Change 6.4 (2016). paper

   Justin Farrell.

2. Enhancing Air Quality Prediction with Social Media and Natural Language Processing. ACL 2019. paper

   Jyun-Yu Jiang et al.