TLDR: Papers fall into three main clusters, and are about using social media to characterize and measure:
(a) mental and physical health (for example, heart disease),
(b) gender, age and personality (best prediction, insight examples), and
(c) papers about methods (best intro).

Up-to-date Google Scholar is here, and all the publications of our lab are here (below last updated 10/2018). Resources can be found on LexHub.org, including some neat tutorials on how to plan and execute language analyses.

†† marks senior author status on papers with first-author-last-author emphasis (as suggested by Tscharntke, Hochberg, Rand, Resh & Krauss, 2007).


depression.jpg

Measuring Depression Through Social Media

We have run a number of projects to better understand the manifestation of mental illness in social media language, and how to use the social media to predict it--even ahead of the occurrence of its first documentation in the medical record. 

#2018

Eichstaedt, J. C., Smith, R. J., Merchant, R. M., Ungar, L. H., Crutchley, P., Daniel Preotiuc-Pietro, D., Asch, D. A., & Schwartz, H. A. (2018) Facebook language predicts depression in medical records. Proceedings of the National Academy of Sciences.

#2017

[pdf] Guntuku, S. C., Yaden, D. B., Kern, M. L., Ungar, L. H., & Eichstaedt, J. C. †† (2017). Detecting depression and mental illness on social media: an integrative review. Current Opinion in Behavioral Sciences, 18, 43-49.

# 2015

[pdf] Preotiuc-Pietro, D., Eichstaedt, J.C., Park, G., Sap, M., Smith, L., Tobolsky, V., Schwartz, H. A., & Ungar, L. H. (2015). The Role of Personality, Age and Gender in Tweeting about Mental Illnesses. Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, NAACL.

# 2014

 [pdf] Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Park, G., Sap, M., Stillwell, D., Kosinski, M., Ungar, L. H. (2014). Towards Assessing Changes in Degree of Depression through Facebook. ACL 2014 Workshop on Computational Linguistics and Clinical Psychology, 118. 


psychsciencemap

Twitter Predicts Community Heart Disease

We show that Twitter can capture more information about county-level atherosclerotic heart disease than solid epidemiological models that include socioeconomic status, demographics and health variables, like smoking, diabetes and hypertension. Hostility and disengagement in particular are associated with risk. Engagement, positive emotions and optimism show protective associations. 

# 2018

[pdf] Eichstaedt, J. C., Schwartz, H. A., Giorgi, S., Kern, M. L., Park, G., Sap, M., Labarthe D.R., Larson, E. E., Seligman, M. E, P., & Ungar, L. H. (2018, March 15). More Evidence that Twitter Language Predicts Heart Disease: A Response and Replication. PsyArXiv. https://doi.org/10.31234/osf.io/p75ku

# 2015

** [pdf] Eichstaedt, J. C., Schwartz, H. A., Kern, M. L., Park, G., Labarthe, D. R., Merchant, R. M., Jha, S., Agrawal, M., Dziurzynski, L. A., Sap, M., Weeg, C., Larson, E. E., Ungar, L. H., & Seligman, M. E. (2015). Psychological Language on Twitter Predicts County-Level Heart Disease Mortality. Psychological Science.

[pdf][big pdf with supplement] -  [OPEN DATA]

Press: Press Release, Washington Post, The New Yorker, and, importantly, The Onion.

See here for a tutorial on how to load and work with the associated data set.


Measuring Well-Being through Social Media

We've used Twitter and Facebook to assess county and person-level life satisfaction and well-being, using well-being data collected through surveys to train our models. It can be done, particularly if one adds socioeconomic information to the prediction models. The language most associated with life satisfaction looks roughly like you'd expect based on the the well-being literature, reflecting higher income, better jobs but also more time spent doing fun and healthy things.

# 2018

[pdf] Obschonka, M., Lee, N., Rodríguez-Pose, A., Eichstaedt, J. C., & Ebert, T. (2018). Big Data, artificial intelligence and the geography of entrepreneurship in the United States. Centre for Economic Policy Research. 

# 2016

[pdf] Smith, L.K., Giorgi, S., Solanki, R., Eichstaedt, J. C., Schwartz, A. H., Abdul-Mageed, M., Buffone, A., & Ungar, L. H. (2016). Does 'well-being translate on Twitter?' Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)

[pdf] Schwartz, H. A., Sap, M., Kern, M. L., Eichstaedt, J. C., Kapelner, A., Agrawal, M., Blanco, E., Dziurzynski, L., Park, G., Stillwell, D., Kosinski, D., Seligman, M.E.P., Ungar, L.H. (2016). Predicting Individual Well-Being Through the Language of Social Media. Pacific Symposium on Biocomputing 21:516-527.

# 2013

[pdfEichstaedt, J. C. *, Schwartz, H. A.*, Kern, M. L., Dziurzynski, L., Lucas, R. E., Agrawal, M., Park, G. J., Lakshmikanth, S. K., Jha, S., Seligman, M. E. P., & Ungar, L. H. (2013). Characterizing Geographic Variation in Well-Being using Tweets. In Seventh International AAAI Conference on Weblogs and Social Media (ICWSM). Boston, MA. (* Equal contribution.)

Press: The Atlantic Blog


2018-09-01 18_48_10-Window.png

Psychological Traits beyond Personality

An extension of the earlier work on personality, we have used Facebook and Twitter to study locus of control, pathogenic empathy and temporal orientation.

# 2017

[pdf] [poster] Jaidka, K., Buffone, A., Giorgi, S., Eichstaedt, J. C., Rouhizadeh, M., & Ungar, L. H. (2018). Modeling and visualizing locus of control with Facebook language. Proceedings of the Twelfth International AAAI Conference on Web and Social Media (ICWSM).

[pdf] Abdul-Mageed, M., Buffone, A., Peng, H., Eichstaedt, J. C., & Ungar, L. H. (2017). Recognizing Pathogenic Empathy in Social Media. In Proceedings of the Twelfth International AAAI Conference on Web and Social Media (ICWSM). pp. 448-451.

# 2016

[pdf] Park, G., Schwartz, H. A., Sap, M., Kern, M. L., Weingarten, E., Eichstaedt, J. C., Berger, J., Stillwell, D. J., Kosinski, M., Ungar, L. H. & Seligman, M. E. (2015). Living in the Past, Present, and Future: Measuring Temporal Orientation with Language. Journal of Personality.

# 2015

[pdf] Schwartz, H. A., Park, G., Sap, M., Weingarten, E., Eichstaedt, J.C., Kern, M., Stillwell, D., Kosinski, M., Berger, J., Seligman, M., & Ungar, L. (2015). Extracting Human Temporal Orientation from Facebook Language. NAACL-2015: Conference of the North American Chapter of the Association for Computational Linguistics.


Measuring Personality through Facebook, not Surveys

We show that Facebook-language-based predictions of personality are about as good as a friend's rating. 

# 2014

** [pdf]  Park, G., Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Kosinski, M., Stillwell, D. J., Ungar, L. H., & Seligman, M. E. P. (2014). Automatic personality assessment through social media language. Journal of Personality and Social Psychology.

Press: neuroskeptic, New York Magazine


Personality, Gender & Age

We identified the word, phrases and topics most correlated with gender, different age ranges, dimensions of personality, temporal orientation and locus of control across 75,000 users. Turns out this a great tool to understand the thoughts and behaviors that characterize personality, and different stages of life. 

# 2016

[pdf] Park, G., Yaden, D. B., Schwartz, H. A., Kern, M. L., Eichstaedt, J. C., Kosinski, M., ... & Seligman, M. E. (2016). Women are Warmer but No Less Assertive than Men: Gender and Language on Facebook. PloS ONE, 11(5), e0155885.

Placing gender language topics in the emotional circumplex. Neat figures.

Press: Press ReleaseNew York Times,

# 2014

[pdf] Kern, M. L., Eichstaedt, J. C., Schwartz, H. A., Dziurzynski, L., Ungar, L. H., Stillwell, D. J., … & Seligman, M. E. P. (2014). The online social self: An open vocabulary approach to personality. Assessment, 21, 158-169. 

[pdf] Kern, M. L., Eichstaedt, J. C., Schwartz, H. A., Park, G., Ungar, L. H., Stillwell, D. J., … & Seligman, M. E. P. (2014). From “sooo excited!!!” to “so proud”: Using language to study development. Developmental Psychology, 50, 178-188 

# 2013

** [pdf] Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Ramones, S. M., Agrawal, M., Shah, A., Kosinki, M., Stillwell, D., Seligman, M. E. P., & Ungar, L. H. (2013). Personality, gender, and age in the language of social media: The open-vocabulary approach. PLOS ONE, 8, e73791.  online 

[pdf] Schwartz, H. A., Eichstaedt, J. C., Dziurzynski, L., Kern, M. L., Blanco, E., Kosinski, M., Stillwell, D., Seligman, M. E. P., & Ungar, L. H. (2013). Toward Personality Insights from Language Exploration in Social Media. In AAAI Spring Symposium Series. Stanford, CA. 

Press:  Press release, Wired, Slate, New York Times Blog, Psychologie Heute, Business Insider, Daily Mail, MIT Technology Review, USA Today, terrible


Methods in Psychology

# 2016

[pdf] Kern, M. L., Park, G., Eichstaedt, J. C., Schwartz, H. A., Sap, M., Smith, L. K., & Ungar, L. H. (2016). Gaining Insights From Social Media Language: Methodologies and Challenges. Psychological Methods.

A general introduction to how we some analyses in the World Well-Being Project.


choosingwords

Methods in Natural Language Processing

Many social scientists (including us) use relatively simple "word count" methods to measure psychological variables. Machine-learning and NLP-based methods can improve on these approaches, sometimes modestly, sometimes dramatically.

#2017

[pdf] Schwartz, H. A., Giorgi, S., Sap, M., Crutchley, P., Ungar, L., & Eichstaedt, J. C. (2017). DLATK: Differential language analysis ToolKit. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (pp. 55-60).

Our entire code-base has been released open source, thanks to a heroic effort by Andy and Sal Giorgi. See dlatk.wwbp.org. Now even in docker containers! 

See here for tutorials.

# 2016

[pdf] Preotiuc-Pietro, D., Schwartz, H.A., Park, G., Eichstaedt, J. C., Kern, M., Ungar, L., Shulman, E.P. (2016). Modelling Valence and Arousal in Facebook Posts. Proceedings of the Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA), NAACL.

# 2014

[pdf] Sap, M., Park, G., Eichstaedt, J. C., Kern, M. L., Stillwell, D. J., Kosinski, M., Ungar, L. H., & Schwartz, H. A. (2014). Developing age and gender predictive lexica over social media. Conference on Empirical Methods in Natural Language Processing (EMLNP). Doha, Qatar. 

# 2013

[pdf] Schwartz, H. A., Eichstaedt, J. C., Dziurzynski, L., Kern, M. L., Blanco, E., Ramones, S., Seligman, M. E. P., & Ungar, L. H. (2013). Choosing the Right Words: Characterizing and Reducing Error of the Word Count Approach. In *SEM-2013: Second Joint Conference on Lexical and Computational Semantics. 


Spiritual Experiences

David Yaden is leading a number of projects to characterize self-transcendent, spiritual and mystical experiences.

# 2017

[pdf] Yaden, D. B., Eichstaedt, J. C., Kern, M. L., Smith, L. K., Buffone, A., Stillwell, D. J., Kosinski, M., Ungar, L.H., Seligman, M.E. & Schwartz, H. A. (2017). The Language of Religious Affiliation: Social, Emotional, and Cognitive Differences. Social Psychological and Personality Science, 1948550617711228.

[pdf] Yaden, D. B., Le Nguyen, K. D., Kern, M. L., Wintering, N. A., Eichstaedt, J. C., Schwartz, H. A., Buffone, A.E., Smith, L.K., Waldman, M.R., Hood Jr, R.W., & Newberg, A. B. (2017). The noetic quality: A multimethod exploratory study. Psychology of Consciousness: Theory, Research, and Practice, 4(1), 54.

# 2016

[pdf] Yaden, D. B., Iwry, J., Slack, K. J., Eichstaedt, J. C., Zhao, Y., Vaillant, G. E., & Newberg, A. B. (2016). The overview effect: Awe and self-transcendent experience in space flight. Psychology of Consciousness: Theory, Research, and Practice, 3(1), 1.

This is about space. I repeat: space.

Press: Press ReleaseWashington PostNew York Magazine, NPR, Fox News, and whatnot.

[pdf] Yaden, D. B., Le Nguyen, K. D., Kern, M. L., Belser, A. B., Eichstaedt, J. C., Iwry, J., ... & Newberg, A. B. (2016). Of Roots and Fruits A Comparison of Psychedelic and Nonpsychedelic Mystical Experiences. Journal of Humanistic Psychology. p. 0022167816674625

# 2015

[pdf] Yaden, D. B., Eichstaedt, J. C., Schwartz, H. A., Kern, M. L., Le Nguyen, K. D., Wintering, N. A., Hood, R. W., Jr., & Newberg, A. B. (2015). The Language of Ineffability: Linguistic Analysis of Mystical Experiences. Psychology of Religion and Spirituality


The Mechanics of Human Achievement

This is a fun paper... we argue that you can analogize achievement to distance, skill to speed, and talent to acceleration, and close the metaphorical loop with the equations of basic mechanics. This framework organizes a long list of individual difference variables into these three classes, and makes testable predictions about which matters more for what outcome on which time-scale.

# 2015

[pdf] Duckworth, A. L., Eichstaedt, J. C., & Ungar, L. H. (2015), The Mechanics of Human Achievement. Social and Personality Psychology Compass, 9, 359–369.

And now, this.


Commentary & Popular Press Articles

# 2018

[pdf] Yaden, D. B., Eichstaedt, J. C., & Medaglia, J. D. (2018). The Future of Technology in Positive Psychology: Methodological Advances in the Science of Well-Being. Frontiers in psychology9, 962.

# 2016

[pdf] [html]  Eichstaedt, J.C. (2016). Using Social Media to Assess Health from Afar. Scientific American Mind, March/April 2016.

An accessible overview ( I hope) of the work of the World Well-Being Project, and related research. 

# 2015

[link] - Eichstaedt, J. C. (2015, March). Big Data and the World of Social Media: Lessons Learned at the Intersection of Computer and Psychological Sciences. APS Observer.

My semi-humorous take on all of this.