[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-578933-105":59,"doc-detail-578933-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","leveraging-interview-informed-llms-to-model-survey-responses-comparative-insights-from-ai-generated-and-human-data","Leveraging Interview-Informed LLMs to Model Survey Responses - Comparative Insights from AI-Generated and Human Data","","Mixed methods research must align qualitative and quantitative structures, yet measuring characteristics and individual response patterns remains difficult. This study evaluates whether interview-guided large language models (LLMs) can predict human survey responses, using the Behavioral Regulations in Exercise Questionnaire (BREQ) and interviews from after-school staff. Findings show accurate overall response patterns with reduced variability versus humans. Interview-informed prompts improve response diversity for some models, while demographic effects are weaker. Item-level gaps grow for negatively worded items, and person-level performance varies, but psychometric structure reconstruction fails despite trend replication.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/leveraging-interview-informed-llms-to-model-survey-responses-comparative-insights-from-ai-generated-and-human-data/578933/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/leveraging-interview-informed-llms-to-model-survey-responses-comparative-insights-from-ai-generated-and-human-data/578933.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does the study use interview information with LLMs to model survey responses?","Question",{"text":112,"@type":113},"The LLMs are guided by personal interviews collected from after-school program staff, then used to generate synthetic survey responses for the BREQ and compare them with human responses.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What differences are observed between LLM-generated responses and human data?",{"text":117,"@type":113},"LLMs reproduce overall response patterns, but they show lower variability than humans.",{"name":119,"@type":110,"acceptedAnswer":120},"Which factors most affect alignment between LLM outputs and human responses?",{"text":121,"@type":113},"Interview content improves alignment and response diversity for some models, while demographic information has less impact on alignment accuracy. Item-level discrepancies are larger for negatively worded questions.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},578933,1792927055,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":26,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI‑Generated and Human Data  \nJihong Zhang University of Arkansas Fayetteville , U.S. [jzhang@uark.edu](jzhang@uark.edu)  \nXinya Liang University of Arkansas Fayetteville, U.S. [xl014@uark.edu](xl014@uark.edu)  \nAnqi Deng University of Arkansas Fayetteville, U.S. [adeng@uark.edu](adeng@uark.edu)  \nNicole Bonge University of Arkansas Fayetteville, U.S. [ngbonge@uark.edu](ngbonge@uark.edu)  \nLin Tan  \nUniversity of Arkansas Fayetteville, U.S. [lintan@uark.edu](lintan@uark.edu)  \nLing Zhang University of Wyoming Laramie , U.S. lingzhangelaine@gmail.com  \nNicole Zarret University of South Carolina  \nColumbia , U.S. [zarrettn@mailbox.sc.edu](zarrettn@mailbox.sc.edu)  \nMixed methods research integrates quantitative and qualitative data but faces challenges in aligning their distinct structures, particularly in examining measurement characteristics and individual response patterns. Advances in large language models (LLMs) offer promising solutions by generating synthetic survey responses informed by qualitative data. This study investigates whether LLMs, guided by personal interviews, can reliably predict human survey responses, using the Behavioral Regulations in Exercise Questionnaire (BREQ) and interviews from after-school program staff as a case study. Results indicate that LLMs capture overall response patterns but exhibit lower variability than humans. Incorporating interview data improves response diversity for some models (e.g., Claude, GPT), while well-crafted prompts and low-temperature settings enhance alignment between LLM and human responses. Demographic information had less impact than interview content on alignment accuracy. Item-level analysis revealed higher discrepancies for negatively worded questions, suggesting LLMs struggle with emotional nuance. Person-level differences indicated varying model performance across respondents, highlighting the role of interview relevance over length. Despite replicating individual item trends, LLMs faltered in reconstructing the test’s psychometric structure. These findings underscore the potential of interview-informed LLMs to bridge qualitative and quantitative methodologies while revealing limitations in response variability, emotional interpretation, and psychometric  \n1 Journal of Educational Data Mining, Volume 18, No 1, 2026  \nfidelity. Future research should refine prompt design, explore bias mitigation, and optimize model settings to enhance the validity of LLM-generated survey data in social science research. The R code and the supplementary materials are available on the OSF platform (DOI:10.17605/OSF.IO/AFQG3) .  \nKeywords: quantitative data, qualitative data, LLM-driven interview, survey, behavioral regulations in exercise  \n1. INTRODUCTION  \nMixed methods design is a widely used research approach in psychology and education (Bishop, 2015 ; Johnson et al., 2007 ; Powell et al., 2008) due to the complementary strengths of integrating both quantitative and qualitative approaches. The framework of mixed methods study design requires the rigorous collection and analysis of both quantitative and qualitative data to answer research questions and test hypotheses (Creswell & Clark, 2017). However, because of the structural differences between qualitative (e.g., open-ended responses, textual richness, contextdependent interpretations) and quantitative (e.g., numeric ratings, standardized scales, fixedresponse options; Schoonenboom, 2023) data, comparative analysis between quantitative and qualitative information—especially for examining measurement characteristics such as response formatting or question wording, as well as person-level attributes such as individual response styles and subjective interpretations—remains challenging, which hinders the broader adoption of mixed methods design (J. Wang et al., 2024) . With the advent of large language models (LLMs) in natural language understa","cbCailMGmXBELSzj","https://ap.wps.com/l/cbCailMGmXBELSzj","pdf",678703,24,"English","# INTRODUCTION\n## Mixed methods design and the alignment challenge\n## GenAI and persona-driven synthetic survey responses\n## Prior work and open problems in small-sample and Likert responses","[{\"question\":\"How does the study use interview information with LLMs to model survey responses?\",\"answer\":\"The LLMs are guided by personal interviews collected from after-school program staff, then used to generate synthetic survey responses for the BREQ and compare them with human responses.\"},{\"question\":\"What differences are observed between LLM-generated responses and human data?\",\"answer\":\"LLMs reproduce overall response patterns, but they show lower variability than humans.\"},{\"question\":\"Which factors most affect alignment between LLM outputs and human responses?\",\"answer\":\"Interview content improves alignment and response diversity for some models, while demographic information has less impact on alignment accuracy. Item-level discrepancies are larger for negatively worded questions.\"}]","Leveraging Interview-Informed LLMs to Model Survey Responses - Comparative Insights from AI-Generated and Human Data | PDF",1792034674]