[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-292976-105":59,"doc-detail-292976-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","interspeech-2022-towards-automated-dialog-personalization-using-mbti-personality-indicators","Interspeech 2022 - Towards Automated Dialog Personalization using MBTI Personality Indicators","","Conversational interfaces increasingly require personalization to improve user acceptance, satisfaction, and trust. This work adapts chatbot behavior using Myers-Briggs personality type indicators and studies how a chatbot that mirrors a user’s personality affects usability. Personality is predicted from chat messages using a pre-trained language model, avoiding extensive resource engineering. Analyzing aligned vs. misaligned personality conditions shows significant gains in satisfaction, perceived naturalness, recommendation likelihood, appropriateness, and trustworthiness. Comparing language models and training objectives, contrastive learning outperforms prior methods, achieving strong F1 on dichotomies.",{"@graph":69,"@context":123},[70,84,106],{"@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/interspeech-2022-towards-automated-dialog-personalization-using-mbti-personality-indicators/292976/",{"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/interspeech-2022-towards-automated-dialog-personalization-using-mbti-personality-indicators/292976.png","ImageObject",300,407,{"name":92,"@type":93},"\tWilliam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",16,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"How does the work personalize chatbot behavior for users?","Question",{"text":113,"@type":114},"It uses Myers-Briggs personality type indicators to adapt chatbot behavior so the system mirrors the user’s personality.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is user personality predicted in this study?",{"text":118,"@type":114},"Personality is predicted from user chat messages using a pre-trained language model, rather than composing many resources such as lexicons.",{"name":120,"@type":111,"acceptedAnswer":121},"What is the main effect of aligning the chatbot’s personality with the user’s?",{"text":122,"@type":114},"Alignment significantly improves usability factors including satisfaction, perceived naturalness, recommendation likelihood, appropriateness, and trustworthiness.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},292976,1789658205,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":24,"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":130,"read_time":144,"preview_page_count":4},5909887254083,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Interspeech 2022  \n18-22 September 2022, Incheon, Korea  \nTowards Automated Dialog Personalization using MBTI Personality Indicators  \nDaniel Fernau† Stefan Hillmann †⋆ Nils Feldhus⋆ Tim Polzehl⋆†  \n† Technische Universität Berlin  \n⋆ German Center For Artificial Intelligence (DFKI)  \n{[daniel.fernau@campus.|stefan.hillmann@}tu-berlin.de](daniel.fernau@campus.|stefan.hillmann@}tu-berlin.de) , {[nils.feldhus|tim.polzehl}@dfki.de](nils.feldhus|tim.polzehl}@dfki.de)  \nAbstract  \nAs conversational interfaces mature in both capacity and usage, the need to personalize towards specific user characteristics becomes apparent, in order to improve users’ acceptance, satisfaction and trust in the conversations. We utilize the concept of Myers-Briggs personality type indicators in order to adapt chatbot behavior. In a user study, we investigate the impact and realization of the so-called “law of attraction” by providing users with a chatbot that mirrors their own personality. This entails predicting the personality from the user behavior, in this work chat messages, by utilizing a pre-trained language model rather than composing many resources like lexicons. We conduct a user study with aligned and misaligned personality and analyze the effect on usability. Results show that alignment significantly improves major usability factors such as satisfaction, perceived naturalness, recommendation likelihood, appropriateness and trustworthiness of our interaction. Further, comparing different language models, contrastive learning approaches outperform previous methods. Predicting the thinking vs. feeling and introversion vs. extroversion indicator dichotomies, we achieve 76.14% F1 and 69.11% F1 , respectively, with setting a new stateof-the-art performance in the literature for the former. Finally, our work adds transparency to the design of linguistic personality cues, hitherto rarely reported in the literature.  \nIndex Terms: personality recognition, MBTI, traits, transfer learning, language modeling  \n1. Introduction  \nAs chatbots become a more significant factor in customer interaction today, they interact with humans in various settings on messaging platforms and websites [1, 2] . Organizations start to realize the potential of chatbots to automate their customer service operations and hence reduce costs [3] . However, the quality of today’s systems does not seem to meet customer expectations [2] . One key obstacle reported is the lack of humanness and naturalness [4, 2] . Studies on human-computer interactions have identified personality as an essential factor to overcome the issue [5] . A person’s language can provide information about the user’s personality [6, 7, 8] .  \nPersonality is generally seen as a stable pattern that provides a measure for a person’s behavior [9] . Traditionally, personality is assessed by questionnaires; current approaches, however, make it possible to use human-generated data from social media or online forums [7] . One way to investigate personality is the application of Myers-Briggs Type Indicator (MBTI), a personality theory classifying people into the combination of four types, resulting in one of 16 distinct classifications [10] . This distinction leads to a difference in the meaning of each combination. To provide transparency, we used the Open Extended Jungian Type Scales (OEJTS) item set [11] for assessment rather than proprietary MBTI Form M (93 items) [12] .  \nEssentially, the MBTI consists of four dichotomies  \n1. Extroversion (E) vs. Introversion (I)  \n2. Sensing (S) vs. Intuition (N)  \n3. Thinking (T) vs. Feeling (F)  \n4. Judging (J) vs. Perceiving (P)  \nAccording to John et al. (1988), a modern approach to infer personality is inferring it from language based on the lexical hypothesis [8] which states that each person has different opinions and preferences which are expressed in a person’s language. This has been supported by many studies, e.g [13, 14, 6] allocating specific expressions, word lists ","cbCaivayROcsRZ02","https://ap.wps.com/l/cbCaivayROcsRZ02","pdf",224526,"English","# Introduction\n## Background and motivation\n## MBTI framework and assessment choices\n## Language-based personality inference\n# Contributions and study setup\n## User study design\n## Personality prediction methods\n## Personalization and evaluation outcomes","[{\"question\":\"How does the work personalize chatbot behavior for users?\",\"answer\":\"It uses Myers-Briggs personality type indicators to adapt chatbot behavior so the system mirrors the user’s personality.\"},{\"question\":\"How is user personality predicted in this study?\",\"answer\":\"Personality is predicted from user chat messages using a pre-trained language model, rather than composing many resources such as lexicons.\"},{\"question\":\"What is the main effect of aligning the chatbot’s personality with the user’s?\",\"answer\":\"Alignment significantly improves usability factors including satisfaction, perceived naturalness, recommendation likelihood, appropriateness, and trustworthiness.\"}]","Interspeech 2022 - Towards Automated Dialog Personalization using MBTI Personality Indicators | PDF",13]