[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-657637-105":59,"doc-detail-657637-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","time-series-affinity-diagrams-via-generative-ai-paper","Time-Series Affinity Diagrams via Generative AI - paper","","Time-series affinity diagrams are used to analyze how risk perception changes over time, but manual grouping and diagram construction are labor-intensive. This study compares affinity diagram outputs produced manually versus those generated by generative AI, using qualitative analysis to evaluate the challenges of automation. Results show that even with the same model and prompt, generative AI can yield variable configurations, potentially omitting or consolidating risks and mismatching input versus grouped outputs.",{"@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/time-series-affinity-diagrams-via-generative-ai-paper/657637/",{"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/time-series-affinity-diagrams-via-generative-ai-paper/657637.png","ImageObject",300,407,{"name":92,"@type":93},"cryingin4k","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-26",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},"What problem does the study address about affinity diagramming over time?","Question",{"text":112,"@type":113},"Manual time-series affinity diagram analysis is time-consuming. The study targets the difficulty of automating data grouping and diagram construction for changes in risk perception.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the comparison between manual and AI methods conducted?",{"text":117,"@type":113},"The study generates time-series affinity diagram outputs using the time-series affinity diagram method both manually and with generative AI, then compares the resulting risk configuration diagrams qualitatively.",{"name":119,"@type":110,"acceptedAnswer":120},"What kinds of differences can generative AI introduce in the outputs?",{"text":121,"@type":113},"Generative AI may produce varying outputs under the same model and prompt, such as omitting risks deemed unnecessary, consolidating minor risks into a different category label, or producing grouped outputs that do not match the number of input risks.","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},657637,1792985737,{"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":39,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":46},137458181193,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Time-Series Affinity Diagrams via Generative AI  \nMinato Ozawa * , Hideki Goromaru *  \nAbstract  \nIn recent years, the novel coronavirus has caused a global health crisis. As of 2026, more than six years after its emergence, the legal classification ofCOVID-19 under infectious disease laws has been relaxed, daily life has largely returned to pre-pandemic conditions, and the outbreak has subsided. Therefore, this study conducts a time-series analysis using affinity diagrams, focusing on changes in risk perception related to the impact ofCOVID-19. While structuring data enables a detailed analysis of such changes, this process is extremely time-consuming when performed manually. Generative AI can significantly reduce this burden, and numerous studies have applied this approach. However, the differences between results obtained through traditional manual analysis and those generated by AI in time-series affinity diagram analysis remain unclear. In this study, we compare risk configuration diagrams produced by the time-series affinity diagram method when performed manually and when generated by AI. The results indicate that generative AI can produce varying outputs even when the same model and prompt are used, and this variability may influence the final outcomes. For example, certain risks may be omitted if deemed unnecessary, multiple minor risks may be consolidated into a single category with a different label, or the number of input risks may not match the number of grouped outputs. This study focuses on qualitative analysis to examine the challenges associated with automating this process using generative AI.  \nKeywords: Generative AI, Covid-19, Affinity Diagram, Clustering  \n1 Introduction  \nThe COVID-19 pandemic, which began in 2020 [1], was declared over in 2023 following the World Health Organization’s (WHO) termination of the Public Health Emergency of International Concern (PHEIC) [2], leading to a gradual stabilization of social conditions. However, this transition created a discrepancy in risk perception, as the objective risk of infection remained high [3].In addition, a method has been proposed that applies affinity diagramming to risk perception for time-series analysis [4] . This approach is used to construct a multi-layered structure of risks. Furthermore, emerging methods utilizing generative AI, such as ChatGPT [5], have attracted increasing attention. Generative AI leverages natural language processing to understand textual data and generate new content. Consequently, it has the potential to serve as an effective tool for tasks such as data grouping, including timeseries affinity diagramming. However, no studies have yet examined the effectiveness of applying generative AI in this context.In this study, we aim to capture changes in risk perception over multiple years by automating the grouping process—traditionally performed manually—using generative AI, and to examine the differences among various generative AI  \n* Chiba Institute of Technology, Chiba, Japan  \nmodels.  \n2 Related Work  \n2.1 Analytical Tools Prior to the Advent of Generative AI  \nOne method for analyzing state transitions over time is the time-series event-related diagram developed by ImSAFER (Improvement SAFER) [6] . The ImSAFER diagram represents time on the vertical axis and actors (entities performing actions) on the horizontal axis, enabling the tracking of events over time to identify potential issues. This method is particularly well-suited for detecting problematic events involving actions that deviate from normal behavior. Another approach is the time-series affinity diagram method, which applies affinity diagramming to timeseries analysis [3]. However, these analytical methods are typically performed manually and are therefore time-consuming. Z. Pan et al. [7] proposed a data-driven method for predicting COVID-19 cases by integrating historical time-series data with Google Search Trends, without relying on complex mathematical models","cbCais3I6MVaAKpu","https://ap.wps.com/l/cbCais3I6MVaAKpu","pdf",905653,"English","# Introduction\n# Related Work\n## Analytical Tools Prior to the Advent of Generative AI\n## Analysis Using Generative AI","[{\"question\":\"What problem does the study address about affinity diagramming over time?\",\"answer\":\"Manual time-series affinity diagram analysis is time-consuming. The study targets the difficulty of automating data grouping and diagram construction for changes in risk perception.\"},{\"question\":\"How is the comparison between manual and AI methods conducted?\",\"answer\":\"The study generates time-series affinity diagram outputs using the time-series affinity diagram method both manually and with generative AI, then compares the resulting risk configuration diagrams qualitatively.\"},{\"question\":\"What kinds of differences can generative AI introduce in the outputs?\",\"answer\":\"Generative AI may produce varying outputs under the same model and prompt, such as omitting risks deemed unnecessary, consolidating minor risks into a different category label, or producing grouped outputs that do not match the number of input risks.\"}]","Time-Series Affinity Diagrams via Generative AI - paper | PDF"]