Dr. Chen is a postdoctoral research fellow at the Department of Health Policy in the Stanford School of Medicine. Her research focuses on examining machine learning techniques with novel data sources and is developing new algorithmic fairness and mental health projects.

Professional Education

  • Doctor of Philosophy, University Of Edinburgh (2021)
  • Master of Science, City University Of Hong Kong (2017)
  • Master, The University of Hong Kong, Linguistics (2013)

Lab Affiliations

All Publications

  • The Effect of User Psychology on the Content of Social Media Posts: Originality and Transitions Matter FRONTIERS IN PSYCHOLOGY Chen, L., Magdy, W., Wolters, M. K. 2020; 11: 526


    Multiple studies suggest that frequencies of affective words in social media text are associated with the user's personality and mental health. In this study, we re-examine these associations by looking at the transition patterns of affect. We analyzed the content originality and affect polarity of 4,086 posts from 70 adult Facebook users contributed over 2 months. We studied posting behavior, including silent periods when the user does not post any content. Our results show that more extroverted participants tend to post positive content continuously and that more agreeable participants tend to avoid posting negative content. We also observe that participants with stronger depression symptoms posted more non-original content. We recommend that transitions of affect pattern derived from social media text and content originality should be considered in further studies on mental health, personality, and social media.

    View details for DOI 10.3389/fpsyg.2020.00526

    View details for Web of Science ID 000531623900001

    View details for PubMedID 32372996

    View details for PubMedCentralID PMC7187751

  • Inspecting Vulnerability to Depression From Social Media Affect FRONTIERS IN PSYCHIATRY Chen, L., Cheng, C. K., Gong, T. 2020; 11: 54


    Affect describes a person's feelings or emotions in reaction to stimuli, and affective expressions were found to be related to depression in social media. This study examined the longitudinal pattern of affect on a popular Chinese social media platform: Weibo. We collected 1,664 Chinese Weibo users' self-reported CES-D scores via surveys and 3 years' worth of Weibo posts preceding the surveys. First, we visualized participants' social media affect and found evidence of cognitive vulnerability indicated by affect patterns: Users with high depression symptoms tended to use not only more negative affective words but also more positive affective words long before they developed early depression symptoms. Second, to identify the type of language that is directly predictive of depression symptoms, we observed ruminations from users who experienced specific life events close to the time of survey completion, and we found that: increased use of negative affective words on social media posts, together with the presence of specific stressful life events, increased a person's risk of developing high depression symptoms; and meanwhile, though tending to focus on negative attributes, participants also incorporated problem-solving skills in their ruminations. These findings expand our understanding of social media affect and its relationship with individuals' risks of developing depression symptoms.

    View details for DOI 10.3389/fpsyt.2020.00054

    View details for Web of Science ID 000523440100001

    View details for PubMedID 32153438

    View details for PubMedCentralID PMC7047149

  • Building a profile of subjective well-being for social media users PLOS ONE Chen, L., Gong, T., Kosinski, M., Stillwell, D., Davidson, R. L. 2017; 12 (11): e0187278


    Subjective well-being includes 'affect' and 'satisfaction with life' (SWL). This study proposes a unified approach to construct a profile of subjective well-being based on social media language in Facebook status updates. We apply sentiment analysis to generate users' affect scores, and train a random forest model to predict SWL using affect scores and other language features of the status updates. Results show that: the computer-selected features resemble the key predictors of SWL as identified in early studies; the machine-predicted SWL is moderately correlated with the self-reported SWL (r = 0.36, p < 0.01), indicating that language-based assessment can constitute valid SWL measures; the machine-assessed affect scores resemble those reported in a previous experimental study; and the machine-predicted subjective well-being profile can also reflect other psychological traits like depression (r = 0.24, p < 0.01). This study provides important insights for psychological prediction using multiple, machine-assessed components and longitudinal or dense psychological assessment using social media language.

    View details for PubMedID 29135991