HKHaein Kong

Haein Kong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Haein Kong has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Examining racial stereotypes in YouTube autocomplete suggestions

    by Eunbin Ha, Haein Kong, Shagun Jhaver

    Autocomplete is a popular search feature that predicts queries based on user input and guides users to a set of potentially relevant suggestions. In this study, we examine what YouTube autocompletes suggest to users seeking information about race on the platform. Specifically, we perform an algorithm output audit of autocomplete suggestions for input queries about four racial groups and examine the stereotypes they embody. Using critical discourse analysis, we identify five major sociocultural contexts in which racial information appears – Appearance , Ability , Culture , Social Equity , and Manner . We found that the participatory nature of YouTube produces a multifaceted representation of race-related content in its search outputs, characterized by enduring historical biases, aggregated discrimination, and interracial tensions, while simultaneously depicting minority resistance and aspirations of a post-racial society. We call for innovations in content moderation policy design and enforcement to address existing racial harms in YouTube search outputs.


  • Open Access

    Predicting Loneliness through Digital Footprints on Google and YouTube

    by Eiman Ahmed, Liyang Xue, Aniket Sankalp, Haein Kong, Arcadio Matos, Vincent Silenzio, Vivek K. Singh

    Loneliness is an increasingly prevalent condition with many adverse effects on health and quality of life. Accordingly, there is a growing interest in developing automated or low-cost methods for triaging and supporting individuals encountering psychosocial distress. This study marks an early attempt at building predictive models to detect loneliness automatically using the digital traces of individuals’ online behavior (Google search and YouTube consumption). Based on a longitudinal study with 92 adult participants for eight weeks in 2021, we find that users’ online behavior can help create automated classification tools for loneliness with high accuracy. Furthermore, we observed behavioral differences in digital traces across platforms. The “not lonely” participants had higher aggregated YouTube activity and lower aggregated Google search activity than “lonely” participants. Our results indicate the need for a further platform-aware exploration of technology use for studies interested in developing automated assessment tools for psychological well-being.