Yueru Yan

Yueru Yan

PhD Student

Indiana University Bloomington

About Me

I am a PhD student in Information Science with a minor in Computer Science at Indiana University Bloomington, advised by Prof. Susan Herring, Prof. Siqi Wu, and Prof. Thai Le. My research lies at the intersection of computational social science and artificial intelligence. I employ computational methods, including natural language processing, statistical analysis, and machine learning, to understand how AI influences human behaviors, particularly in communication and information seeking.

Currently, I'm working on large-scale conversational AI datasets, algorithm auditing, and LLM fairness evaluation. Previously, I worked at the Language Understanding Lab at Samsung Research Center on machine learning approaches for mental health detection.

Download CV

Interests

  • Computational Social Science
  • Social Media Analytics
  • Algorithm Auditing
  • Statistics

Education

  • PhD in Information Science Indiana University Bloomington 2023 – Now
  • MS in Applied Statistics Beijing Normal University 2021 – 2023
  • BS in International Communication and Journalism Beijing Foreign Studies University 2015 – 2019

Papers

Preprints

2025

ShareChat: A Dataset of Chatbot Conversations in the Wild Preprint

Yueru Yan, Tuc Nguyen, Bo Su, Melissa Lieffers, Thai Le

arXiv:2512.17843

A large-scale, cross-platform corpus comprising 142,808 conversations and over 660,000 turns collected from publicly shared URLs across five major platforms: ChatGPT, Claude, Gemini, Perplexity, and Grok.

PDF arXiv
2025

Fairness Evaluation of Large Language Models in Academic Library Reference Services Preprint

Haining Wang, Jason Clark, Yueru Yan, Star Bradley, Ruiyang Chen, Yiqiong Zhang, Hengyi Fu, Zuoyu Tian

arXiv:2507.04224

Evaluates whether LLMs differentiate responses across user identities by prompting six state-of-the-art LLMs to assist patrons differing in sex, race/ethnicity, and institutional role.

PDF arXiv

Under Review

2025

Auditing Algorithmic Personalization in TikTok Comment Sections Under Review

Yueru Yan, Siqi Wu

Designed and built a large-scale TikTok political video & comment dataset (4,691 videos, 10M+ comments) and used LLM to analyze how user ideological leanings influence comment ranking under political videos.

Published

2025

Hardship Streamers in Live Crowdfunding

Yueru Yan, Pnina Fichman

iConference 2025

Analyzed TikTok hardship live streaming where people stream to raise money from 14 creators using topic modeling, sentiment analysis, and thematic coding, finding that multimodal authenticity cues and positive tone relate to stronger sales, hardship storytelling increases viewer retention, and women emphasize hardship and use more negative, faster speech than men.

PDF
2022

A CNN Model with Discretized Mobile Features for Depression Detection

Yueru Yan, Mei Tu, Hongbo Wen

IEEE BSN 2022

Developed and applied sequential machine learning models, including CNN, LSTM, and a custom-designed DEP-CASER model for depression detection, achieving a state-of-the-art accuracy of 0.83.

PDF
2022

Detecting Depression, Anxiety and Mental Stress in One Sequential Model with Multi-task Learning

Shen Zhang, Mei Tu, Yueru Yan, Yimeng Zhuang, Likun Ge, Gaoxia Wei

HCI International 2022 – Late Breaking Papers

Proposed a multi task, sequence based mobile sensing model that jointly predicts depression, anxiety, and stress, achieving 0.78 average accuracy and 0.78 average AUC, and outperforming single task and statistical feature baselines.

PDF