[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-293159-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-293159-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","myers-briggs-personality-classification-from-social-media-text-using-pre-trained-language-models-journal-of-universal-computer-science-vol-28-no-4-2022","Myers-Briggs personality classification from social media text using pre-trained language models - Journal of Universal Computer Science - vol. 28, no. 4 (2022)","","Natural Language Processing methods using pre-trained language models can achieve state-of-the-art performance across downstream tasks. This study applies such approaches to personality classification from text, targeting the Myers-Briggs (MBTI) model. The authors fine-tune Bidirectional Encoder Representations from Transformers (BERT) to perform MBTI classification and compare it with bag-of-words and static word embedding baselines. Results indicate the BERT-based approach significantly outperforms prior text classifiers in multiple evaluation scenarios, including earlier work.",{"@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/myers-briggs-personality-classification-from-social-media-text-using-pre-trained-language-models-journal-of-universal-computer-science-vol-28-no-4-2022/293159/",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/myers-briggs-personality-classification-from-social-media-text-using-pre-trained-language-models-journal-of-universal-computer-science-vol-28-no-4-2022/293159.png","ImageObject",300,407,{"name":42,"@type":43},"Mary Man","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-03","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",19,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What task does the paper focus on?","Question",{"text":63,"@type":64},"It focuses on classifying personality from text using the Myers-Briggs (MBTI) model, applied to social media text.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which model is fine-tuned for MBTI classification?",{"text":68,"@type":64},"The paper fine-tunes a BERT (Bidirectional Encoder Representations from Transformers) model for MBTI classification.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the proposed method compare with traditional text representations?",{"text":72,"@type":64},"The findings indicate BERT-based models significantly outperform bag-of-words and static word embedding approaches across evaluation scenarios.","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},293159,1789660408,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"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":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"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":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144,"preview_page_count":4},7421720224475,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Journal of Universal Computer Science, vol. 28, no. 4 (2022), 378-395 submitted: 1/7/2021, accepted: 21/2/2022, appeared: 28/4/2022 CC BY-ND 4.0  \nMyers-Briggs personality classification from social media text using pre-trained language models  \nVitor Garcia dos Santos  \n(University of São Paulo, Brazil  \n [https://orcid.org/0000-0003-4856-4043](https://orcid.org/0000-0003-4856-4043), [vitorgds95@gmail.com](vitorgds95@gmail.com))  \nIvandré Paraboni  \n(University of São Paulo, Brazil  \n [https://orcid.org/0000-0002-7270-1477](https://orcid.org/0000-0002-7270-1477), [ivandre@usp.br](ivandre@usp.br))  \nAbstract: In Natural Language Processing, the use of pre-trained language models has been shown to obtain state-of-the-art results in many downstream tasks such as sentiment analysis, author identification and others. In this work, we address the use of these methods for personality classification from text. Focusing on the Myers-Briggs (MBTI) personality model, we describe a series of experiments in which the well-known Bidirectional Encoder Representations from Transformers (BERT) model is fine-tuned to perform MBTI classification. Our main findings suggest that the current approach significantly outperforms well-known text classification models based on bag-of-words and static word embeddings alike across multiple evaluation scenarios, and generally outperforms previous work in the field.  \nKeywords: Natural language processing, text classification, Myers-Briggs, MBTI, personality, author profiling  \nCategories: I.2.7  \nDOI: 10.3897/jucs.70941  \n1 Introduction  \nHuman personality-a set of relatively stable behaviour patterns of an individual [Allport and Allport, 1921] -has been the focus of studies in multiple disciplines, and it is wellknown to computer science through personality models such as the Big Five [Goldberg, 1990] and, perhaps to a lesser extent, the Myers-Briggs Type Indicator (MBTI) [Myers, 1962]. Models of this kind associate word choices made by an individual (e.g., a customer, a social media user etc.) to pre-defined personality categories (e.g., extroverts versus introverts), allowing us to assess their personality traits for a wide range of practical applications in both natural language interpretation [dos Santos and Paraboni, 2019, dos Santos et al., 2020] and generation [Teixeira et al., 2014] .  \nPersonality assessment may however require the use of personality inventories (e.g.,[John et al., 1991]) with the aid of specialists, which may become costly in large scale. As an alternative to this, studies in Natural Language Processing (NLP) and related fields have addressed the relation between language use and personality to develop methods for automatically detecting the personality traits of individuals based on text samples that they have written (e.g., on social media etc.) [Plank and Hovy, 2015, Liu et al., 2017, dos Santos et al., 2017, Wu et al., 2020] .  \nPersonality detection from text may be seen as an instance of author profiling, that is, the task of inferring an author’s demographics based on text samples that they have  \ndos Santos V.G., ParaboniI.: Myers-Briggs personality classification ... 379  \nauthored [Rangel et al., 2020, Polignano et al., 2020, Price and Hodge, 2020, LópezSantill [et. al](et. al)., 2020, Silva and Paraboni, 2018a, dos Santos et al., 2019, Delmondes Neto and Paraboni, 2021]. As in other profiling tasks (e.g., author’s gender or age detection), studies of this kind are usually implemented with the aid of supervised machine learning based on text corpora labelled with personality information. The issue of personality classification from text with a specific focus on the MBTI personality model is the subject of the present study.  \nExisting work in MBTI classification from text generally follows much of the same methods seen elsewhere in NLP, which usually comprise the use of a bag-of-words model or, more recently, static word embeddings such as those provided by Word2vec ","cbCaiq4I1DDi5lOV","https://ap.wps.com/l/cbCaiq4I1DDi5lOV","pdf",343459,18,"English","# 1 Introduction\n# 2 Background\n## 2.1 Related work\n## 2.2 Overview of approaches","[{\"question\":\"What task does the paper focus on?\",\"answer\":\"It focuses on classifying personality from text using the Myers-Briggs (MBTI) model, applied to social media text.\"},{\"question\":\"Which model is fine-tuned for MBTI classification?\",\"answer\":\"The paper fine-tunes a BERT (Bidirectional Encoder Representations from Transformers) model for MBTI classification.\"},{\"question\":\"How does the proposed method compare with traditional text representations?\",\"answer\":\"The findings indicate BERT-based models significantly outperform bag-of-words and static word embedding approaches across evaluation scenarios.\"}]","Myers-Briggs personality classification from social media text using pre-trained language models - Journal of Universal Computer Science - vol. 28, no. 4 (2022) | PDF",45]