[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82981-en":3,"doc-seo-82981-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82981,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Depression Symptoms and Relational Patterns in 187k ChatGPT Histories","Large language models are widely used as private conversational systems, yet how people with depressive symptoms use them remains unclear. This study analyzes 187,093 ChatGPT conversations from 766 participants who completed the PHQ-8, comparing moderate-or-higher symptom users (PHQ≥10) with those below threshold (PHQ\u003C10). Higher-PHQ participants showed more mental-health, interpersonal, loneliness, and support-seeking content, distinct language markers, and late-night month-level patterns. Findings indicate that private ChatGPT histories should not be treated as clinical screening data.","arXiv :2607 .05685v 1 [ cs .HC] 6 Jul 2026  \nDepression Symptoms and Relational Patterns in 187k ChatGPT Histories  \nNEIL K. R. SEHGAL, University of Pennsylvania, USA DUNIGAN FOLK, University of Pennsylvania, USA LYLE UNGAR, University of Pennsylvania, USA  \nSHARATH CHANDRA GUNTUKU, University of Pennsylvania, USA  \nLarge language models are increasingly used as private, always-available conversational systems, but little is known about how people with depressive symptoms use them. Building on CSCW work on disclosure and peer support, we examine ChatGPT as an emerging informal support infrastructure: private, persistent, responsive, and available outside ordinary hours. We analyze 187,093 ChatGPT conversations from 766 participants who completed the PHQ-8, comparing those below the moderate-symptom threshold (score of 10) with those at or above it. Higher-PHQ participants used ChatGPT more for mental-health, interpersonal, loneliness, self-focused, and support-seeking conversations, with pronounced late-night and recurring month-level patterns. Their language contained more first-person singular pronouns and absolutist terms. They more often engaged ChatGPT in high-disclosure contexts, but professional redirection was not higher. Language-based prediction was modest and insufficient for screening (AUROC 0.591) . We argue these histories should not be treated as clinical screening data but as evidence LLMs are increasingly used as informal support infrastructure.  \n1 Introduction  \nChatGPT is used for many ordinary tasks such as drafting emails, debugging code, learning concepts, and finding information [5] . It is also used in more personal ways. People ask for advice, disclose concerns, revisit worries, and seek emotionally responsive interaction [10] . This makes it important from a CSCW perspective: ChatGPT is not only an individual productivity tool but a relatively new kind of private conversational infrastructure through which people coordinate with a system that can provide information, advice, validation, and support at any hour.  \nMental-health-adjacent use is a consequential case. People experiencing depressive symptoms may turn to ChatGPT when human support is unavailable, when disclosure feels risky, or when they want low-friction help [10, 21–23] . But ChatGPT is not a peer, clinician, or hotline. It is an always-on system that can sound warm and helpful while also giving confident advice, validating user framings, or failing to clearly redirect users toward professional support.  \nCSCW and HCI research has long examined how people use networked systems to disclose distress, seek support, manage stigma, and find care when formal support is difficult to access [2–4, 16, 17] . This work shows mental-health support is not delivered only through clinical encounters, but can be distributed across peer communities, anonymous disclosures, crisis lines, search practices, and other technology-mediated pathways. ChatGPT extends this landscape in a distinct direction. It offers private, persistent, one-on-one interaction without peers, moderators, volunteers, or clinicians. We therefore examine it as an emerging form of informal support infrastructure rather than as a clinical tool.  \nAuthors’ Contact Information: Neil K. R. Sehgal, [nsehgal@seas.upenn.edu](nsehgal@seas.upenn.edu), University of Pennsylvania, Philadelphia, Pennsylvania, USA; Dunigan Folk, [dunigan@sas.upenn.edu](dunigan@sas.upenn.edu), University of Pennsylvania, Philadelphia, Pennsylvania, USA; Lyle Ungar, [ungar@cis.upenn.edu](ungar@cis.upenn.edu), University of Pennsylvania, Philadelphia, Pennsylvania, USA; Sharath Chandra Guntuku, [sharathg@seas.upenn.edu](sharathg@seas.upenn.edu), University of Pennsylvania, Philadelphia, Pennsylvania, USA.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and th","cbCaitFLHXemB2uQ","https://ap.wps.com/l/cbCaitFLHXemB2uQ","pdf",1021335,2,1,18,"English","en",105,"# Introduction\n# Related Work\n# Method and Research Questions","[{\"question\":\"How does the study evaluate depressive symptoms among ChatGPT users?\",\"answer\":\"It uses PHQ-8 scores completed by 766 participants, comparing those below the moderate-symptom threshold (score of 10) with those at or above it.\"},{\"question\":\"What differences in conversation topics and language appear for higher-PHQ participants?\",\"answer\":\"Higher-PHQ participants used ChatGPT more for mental-health, interpersonal, loneliness, self-focused, and support-seeking conversations, with more first-person singular pronouns and absolutist terms.\"},{\"question\":\"Can language from ChatGPT histories reliably screen for clinical depression?\",\"answer\":\"No. Language-based prediction is modest and insufficient for screening, with AUROC reported as 0.591.\"}]",1784184440,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"depression-symptoms-and-relational-patterns-in-187k-chatgpt-histories","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/depression-symptoms-and-relational-patterns-in-187k-chatgpt-histories/82981/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the study evaluate depressive symptoms among ChatGPT users?","Question",{"text":75,"@type":76},"It uses PHQ-8 scores completed by 766 participants, comparing those below the moderate-symptom threshold (score of 10) with those at or above it.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What differences in conversation topics and language appear for higher-PHQ participants?",{"text":80,"@type":76},"Higher-PHQ participants used ChatGPT more for mental-health, interpersonal, loneliness, self-focused, and support-seeking conversations, with more first-person singular pronouns and absolutist terms.",{"name":82,"@type":73,"acceptedAnswer":83},"Can language from ChatGPT histories reliably screen for clinical depression?",{"text":84,"@type":76},"No. Language-based prediction is modest and insufficient for screening, with AUROC reported as 0.591.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]