[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-293355-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-293355-en":130},{"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":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","its-personal-using-text-to-predict-myers-briggs-personality-types","It’s Personal - Using Text to Predict Myers-Briggs Personality Types","","Investigate whether a computational model can infer Myers-Briggs personality types solely from the text of an individual’s posts. The project trains classification models that map conversational quotes or blog-post text to one of 16 MBTI categories and evaluates predictive performance using sentiment and text-representation approaches. It also builds a generative component aimed at producing quotes aligned with a specified MBTI category. Data are collected from Kaggle/PersonalityCafe, cleaned, then split into 80/20 training and testing sets.",{"@graph":14,"@context":73},[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/its-personal-using-text-to-predict-myers-briggs-personality-types/293355/",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/its-personal-using-text-to-predict-myers-briggs-personality-types/293355.png","ImageObject",300,407,{"name":42,"@type":43},"Mia  ","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",7,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main goal of the project?","Question",{"text":63,"@type":64},"Predict a person’s Myers-Briggs type using only their written text, and explore generating quotes that fit a specified MBTI category.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What dataset and MBTI labels are used?",{"text":68,"@type":64},"The dataset contains 8,675 text posts with MBTI types scraped from PersonalityCafe, covering 16 MBTI categories such as ISTJ, INTP, INFJ, and others.",{"name":70,"@type":61,"acceptedAnswer":71},"How is the text data prepared for modeling?",{"text":72,"@type":64},"The project removes post-break characters (|||), strips URLs, removes mentions of MBTI types, and keeps punctuation, capitalization, and emojis; it also extracts IBM Watson emotion features (anger, joy, sadness, disgust, fear) and uses an 80-20 train-test split.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},293355,1789662843,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":102,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":143,"preview_page_count":4},687207024478,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","It’s Personal: Using Text to Predict Myers-Briggs Personality Types  \nEric Chiu , Hannah Sheetz , Tristrum Tuttle  \nUniversity of Pennsylvania  \n[chiueric@seas.upenn.edu](chiueric@seas.upenn.edu), [hsheetz@seas.upenn.edu](hsheetz@seas.upenn.edu), [tut@seas.upenn.edu](tut@seas.upenn.edu)  \nAbstract  \nCan a computer model figure out a person’s personality just based on the text of their conversations? We want to predict Myers-Briggs personality types purely based on conversational quotes. By building an effective model to categorize conversational quotes as Myers-Briggs type indicators, we will help workers understand themselves and their interactions better, improving productivity and success in the workplace. We will also build a generative model to attempt to create quotes that fall into a specified Myers-Briggs (MB) category.  \n1 Problem Background  \nIn today’s society, more and more companies rely on personality types to help establish a company culture and even streamline recruitment. Companies like Bridgewater and Amazon use MB personality type tests to help them build effective teams and reduce friction among employees. Additionally, knowing ones own personality type is useful for figuring out career plans, building relationships, and achieving more. Because the Meyer’s Briggs test is prone to bias as people are likely to answer questions with how they want to be rather than how they actually are, they can often be placed into the wrong personality type. Our project alleviates this problem of self identification by analyzing sentences said in every day social media interaction and placing them into MBTI personality types.  \n2 Approach  \nIn this project, we attempt to answer two main questions. The first question is,”can we train a model to accurately predict a person’s Myers-Briggs type using just blog posts?” The second question is,”can we train a model to reproduce blog posts with a specified Myers-Briggs type?”  \n2.1 Data Overview  \nOur dataset was from Kaggle, and contains 8,675 instances of people’s text posts and their MBTI type scraped from an online forum called PersonalityCafe. MBTI personality types consist of ISTJ, INTP, ISFJ, INFJ, ISTP, ISFP, INFP, INTJ, ESTP, ESTJ, ESFJ, ENFJ, ESFP, ENTJ, ENTP, and ENFP. In  \ntotal, there are 16 personality types, and for our purposes, 16 different labels. The text for each instance contains the last 50 things a person has posted separated by three vertical lines.  \n2.2 Principle Data Analysis  \nWe looked at the distribution of the number of instances for each MBTI personality type. We found that the number of instances for each MBTI personality type vary greatly, from 42 instances to 1832 instances. At first we thought this was due to the actual distribution of personality types in the real world, but after checking some statistics online and finding that ESTJ, ESFJ, ESTP, andESFP are the most popular MBTI personalities, we concluded that our dataset is not representative of the real world population. Instead, it is representative of the users on the online forum PersonalityCafe. We were also concerned about the unequal number of words per instance for each MBTI personality type. If the number of words for specific personality types were abnormally low, the training dataset for those personality types would be low, thus causing a weaker prediction compared to the other personality types. Luckily, after further analysis, we found that each personality type generally had the same number of words per instance, at an average of 1253 words per instance.  \n2.3 Data Cleaning  \nWe have cleaned the text data by removing the text post break characters (three vertical lines, or |||) . We also removed URLs from the text, because they were highly variable and did not provide useful emotional analysis in IBM Watson. We decided to leave punctuation, capitalization, and emojis in place because they imply certain types of emotion in IBM Watson. After analyzing the data, we realized that many posts ","cbCaiohQ5zHAexUK","https://ap.wps.com/l/cbCaiohQ5zHAexUK","pdf",797734,"English","# Abstract\n# Problem Background\n# Approach\n## Data Overview\n## Principle Data Analysis\n## Data Cleaning\n# Problem 1: Myers-Briggs Prediction\n## Models","[{\"question\":\"What is the main goal of the project?\",\"answer\":\"Predict a person’s Myers-Briggs type using only their written text, and explore generating quotes that fit a specified MBTI category.\"},{\"question\":\"What dataset and MBTI labels are used?\",\"answer\":\"The dataset contains 8,675 text posts with MBTI types scraped from PersonalityCafe, covering 16 MBTI categories such as ISTJ, INTP, INFJ, and others.\"},{\"question\":\"How is the text data prepared for modeling?\",\"answer\":\"The project removes post-break characters (|||), strips URLs, removes mentions of MBTI types, and keeps punctuation, capitalization, and emojis; it also extracts IBM Watson emotion features (anger, joy, sadness, disgust, fear) and uses an 80-20 train-test split.\"}]","It’s Personal - Using Text to Predict Myers-Briggs Personality Types | PDF",15]