[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-293074-105":3,"doc-detail-293074-en":85,"detail-sidebar-cat-0-en-105":102},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":84},105,"en","exploring-personality-aware-interactions-in-salesperson-dialogue-agents","Exploring Personality-Aware Interactions in Salesperson Dialogue Agents","","Dialogue agents in sales require robust understanding of how users with diverse personas shape conversation quality and overall effectiveness. This study examines the influence of Myers-Briggs Type Indicator (MBTI) user personas on interaction dynamics and task performance of a pre-trained sales-oriented dialogue agent. Large-scale testing and analysis evaluate adaptability and personalization across MBTI-defined user types, showing measurable differences in task completion, dialogue naturalness, and interaction flow. The work also releases persona-defined user simulators to support future research.",{"@graph":14,"@context":77},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/exploring-personality-aware-interactions-in-salesperson-dialogue-agents/293074/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/exploring-personality-aware-interactions-in-salesperson-dialogue-agents/293074.png","ImageObject",300,407,{"name":42,"@type":43},"Evangeline","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-25","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69,73],{"name":60,"@type":61,"acceptedAnswer":62},"How does the study model user personas for dialogue evaluation?","Question",{"text":63,"@type":64},"User personas are defined using the Myers-Briggs Type Indicator (MBTI), which categorizes individuals into 16 types via four dimensions (E/I, S/N, T/F, J/P). The experiments use MBTI-based user simulators representing specific personality characteristics.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What dialogue agent is used in the experiments?",{"text":68,"@type":64},"The study uses SALESAGENT, a pre-trained sales-oriented dialogue agent that starts with casual chit-chat before moving into task-oriented conversation.",{"name":70,"@type":61,"acceptedAnswer":71},"What key performance differences are observed across MBTI types?",{"text":72,"@type":64},"Results show significant patterns in interaction dynamics, including differences in task completion rates and dialogue naturalness. For example, extraverted users achieve the highest task success rate (82.7%), while judging users have the lowest (62.1%).",{"name":74,"@type":61,"acceptedAnswer":75},"What resources does the work provide for future research?",{"text":76,"@type":64},"The study contributes by releasing persona-defined user simulators, designed to support further research into scalable personalized dialogue systems beyond the sales domain.","https://schema.org",{"og:url":32,"og:type":79,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":81,"canonical":32},"index,follow",{"doc_id":83,"site_id":7},293074,1789659234,{"code":4,"msg":86,"data":87},"success",{"doc_id":83,"user_id":88,"nickname":42,"user_avatar":89,"doc_module":4,"category_id":90,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":91,"file_id":92,"file_url":93,"file_type":94,"file_size":95,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":96,"language":97,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":98,"faqs":99,"seo_title":100,"seo_description":12,"update_tm":84,"read_time":101,"preview_page_count":4},13056703019662,"https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Exploring Personality-Aware Interactions in Salesperson Dialogue Agents  \nSijia Cheng Wen-Yu Chang Yun-Nung Chen  \nNational Taiwan University, Taipei, Taiwan  \n{r11922184, [f10946031}@csie.ntu.edu.tw](f10946031}@csie.ntu.edu.tw) [y.v.chen@ieee.org](y.v.chen@ieee.org)  \nAbstract  \nThe integration of dialogue agents into the sales domain requires a deep understanding of how these systems interact with users possessing diverse personas. This study explores the in-􀀃uence of user personas, de􀀂ned using the Myers-Briggs Type Indicator (MBTI), on the interaction quality and performance of salesoriented dialogue agents. Through large-scale testing and analysis, we assess the pre-trained agent’s effectiveness, adaptability, and personalization capabilities across a wide range of MBTI-de􀀂ned user types. Our 􀀂ndings reveal signi􀀂cant patterns in interaction dynamics, task completion rates, and dialogue naturalness, underscoring the future potential for dialogue agents to re􀀂ne their strategies to better align with varying personality traits. This work not only provides actionable insights for building more adaptive and user-centric conversational systems in the sales domain but also contributes broadly to the 􀀂eld by releasing persona-de􀀂ned user simulators. These simulators, unconstrained by domain, offer valuable tools for future research and demonstrate the potential for scaling personalized dialogue systems across diverse applications.1  \n1 Introduction  \nDialogue systems are becoming essential in the sales industry, enabling businesses to communicate more effectively with their customers (Adamopoulou and Moussiades, 2020) . These AIdriven systems assist customers by providing product recommendations, answering inquiries, and supporting better purchasing decisions. However, each user is unique, with communication styles that vary according to their personality traits. To create more effective dialogue systems, it is crucial to account for these individual differences. Most conventional conversational systems adopt a “one size  \n1The code and scripts are available at [https://github](https://github) . com/MiuLab/MBTI-User.  \n􀀂ts all” approach, which often results in impersonal interactions. Incorporating an understanding of personality differences can enable dialogue systems to tailor their responses and communication styles, enhancing user satisfaction and engagement.  \nPersonality signi􀀂cantly in􀀃uences conversational preferences. While some individuals favor concise, direct exchanges, others value detailed and exploratory interactions. For instance, Zhang et al.(2018) proposed creating user pro􀀂les based on 5-sentence textual descriptions, such as: “I am a vegetarian. I like swimming. My father used to work for Ford. My favorite band is Maroon5 . I got a new job last month, which is about advertising design.” Current dialogue systems often rely on general user information, such as name, age, preferences, and occupation, to personalize interactions. However, these approaches failed to capture the deeper psychological traits that drive user behavior and shape user preference.  \nTo 􀀂ll in the gap, this study investigates how personality traits, as de􀀂ned by the Myers-Briggs Type Indicator (MBTI), in􀀃uence interaction quality and the performance of sales-oriented dialogue agents. The MBTI is a widely used framework that categorizes individuals into 16 personality types based on four key dimensions: extraversion (E) vs. introversion (I), sensing (S) vs. intuition (N), thinking (T) vs. feeling (F), and judging (J) vs. perceiving (P) . These dimensions shape how individuals gather information, make decisions, and respond to various communication styles.  \nIn this study, we employed SALESAGENT (Chang and Chen, 2024), a pretrained salesoriented dialogue agent, to investigate how different personality traits in􀀃uence conversational outcomes. The goal was to explore whether variations in user personalities lead to distinct interaction pattern","cbCaihMewVtC6x88","https://ap.wps.com/l/cbCaihMewVtC6x88","pdf",194472,12,"English","# Abstract\n# Introduction\n## Dialogue systems in sales\n## Personality and personalization gap\n## Study goal and MBTI framework\n# Method overview\n## SALESAGENT and user simulators\n## Evaluation metrics and analysis\n# Results summary\n## Task success and continuation differences\n# Contributions and future potential","[{\"question\":\"How does the study model user personas for dialogue evaluation?\",\"answer\":\"User personas are defined using the Myers-Briggs Type Indicator (MBTI), which categorizes individuals into 16 types via four dimensions (E/I, S/N, T/F, J/P). The experiments use MBTI-based user simulators representing specific personality characteristics.\"},{\"question\":\"What dialogue agent is used in the experiments?\",\"answer\":\"The study uses SALESAGENT, a pre-trained sales-oriented dialogue agent that starts with casual chit-chat before moving into task-oriented conversation.\"},{\"question\":\"What key performance differences are observed across MBTI types?\",\"answer\":\"Results show significant patterns in interaction dynamics, including differences in task completion rates and dialogue naturalness. For example, extraverted users achieve the highest task success rate (82.7%), while judging users have the lowest (62.1%).\"},{\"question\":\"What resources does the work provide for future research?\",\"answer\":\"The study contributes by releasing persona-defined user simulators, designed to support further research into scalable personalized dialogue systems beyond the sales domain.\"}]","Exploring Personality-Aware Interactions in Salesperson Dialogue Agents | PDF",30,{"code":4,"msg":86,"data":103},[104,108,112,116,121,126,131,133,138,141,145],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":113,"show_sort_weight":114,"slug":115},"Exam",70,"exam",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":118,"show_sort_weight":119,"slug":120},5,"Comic",60,"comic",{"id":122,"doc_module":4,"doc_module_name":25,"category_name":123,"show_sort_weight":124,"slug":125},6,"Technology",50,"technology",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":129,"slug":130},7,"Healthcare",40,"healthcare",{"id":90,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":101,"slug":132},"research-report",{"id":134,"doc_module":4,"doc_module_name":25,"category_name":135,"show_sort_weight":136,"slug":137},9,"Religion & Spirituality",20,"religion-spirituality",{"id":136,"doc_module":4,"doc_module_name":25,"category_name":139,"show_sort_weight":136,"slug":140},"World Cup","world-cup",{"id":142,"doc_module":4,"doc_module_name":25,"category_name":143,"show_sort_weight":142,"slug":144},10,"Lifestyle","lifestyle",{"id":146,"doc_module":4,"doc_module_name":25,"category_name":147,"show_sort_weight":117,"slug":148},19,"General","general"]