{"id":138481,"date":"2025-09-07T03:02:07","date_gmt":"2025-09-07T03:02:07","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/138481\/"},"modified":"2025-09-07T03:02:07","modified_gmt":"2025-09-07T03:02:07","slug":"how-ai-got-a-new-and-improved-personality-usc-viterbi","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/138481\/","title":{"rendered":"How AI Got A New And Improved Personality &#8211; USC Viterbi"},"content":{"rendered":"<p>\u00a0<\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" aria-describedby=\"caption-attachment-79742\" class=\"wp-image-79742 size-full\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2025\/09\/adamsmith_62262_Create_an_illustration_depicting_a_variety_of_665e247a-9c14-4909-ba91-febfcb12a92b_3.png\" alt=\"Bin Han developed a &quot;virtual humans&quot; system focused on extroversion, due to be presented at the prominent IVA 2025 artificial intelligence conference (Photo\/Midjourney).\" width=\"1200\" height=\"600\"  \/><\/p>\n<p id=\"caption-attachment-79742\" class=\"wp-caption-text\">Bin Han developed a \u201cvirtual humans\u201d system focused on extroversion, due to be presented at the prominent IVA 2025 artificial intelligence conference (Photo\/Midjourney).<\/p>\n<p>Artificial intelligence might be picking your stocks or suggesting Netflix movies, but if you ask Bin Han, a third-year Ph.D. computer science student at the USC Viterbi School of Engineering\u2019s <a href=\"https:\/\/www.cs.usc.edu\/\" rel=\"nofollow noopener\" target=\"_blank\">Thomas Lord Department of Computer Science<\/a>, AI still has a long, long way to go in one key area.<\/p>\n<p>Personality.<\/p>\n<p>\u201cThere has been a lot of advancement recently in artificial intelligence technology, but I think we still have room to improve for emotional intelligence,\u201d Han said. \u201cI want to contribute to that domain to make AI more socially intelligent and understand users\u2019 emotions better.\u201d<\/p>\n<p>Han\u2019s work has refined AI\u2019s capacity for social and emotional intelligence. Her recent study, \u201cCan LLMs Generate Behaviors for Embodied Virtual Agents Based on Personality Prompting?\u201d will be presented at the <a href=\"https:\/\/iva.acm.org\/2025\/\" rel=\"nofollow noopener\" target=\"_blank\">25th ACM International Conference on Intelligent Virtual Agents<\/a> (IVA 2025) this September in Berlin. Her USC Viterbi co-authors included Deuksin Kwon, Spencer Lin, Kaleen Shrestha, and Professor <a href=\"https:\/\/viterbi.usc.edu\/directory\/faculty\/Gratch\/Jonathan\" rel=\"nofollow noopener\" target=\"_blank\">Jonathan Gratch<\/a>, director for virtual humans research at the USC Institute for Creative Technologies.<\/p>\n<p>The study proved that AI agents \u2014 virtual human avatars instead of merely text or voice-based AI chatbots \u2014 can adapt to assume certain personality traits, testing these agents on human participants in a controlled experiment. In doing so, Han and the researchers created empathetic AI agents that can accurately reflect people\u2019s personalities in real time, increasing their effectiveness in a variety of real-world scenarios.<\/p>\n<p>Han believes <a href=\"https:\/\/ict.usc.edu\/news\/essays\/on-crafting-personalities-with-code-iva-25\/\" rel=\"nofollow noopener\" target=\"_blank\">her research<\/a> could lead to improved mental health treatments, among other beneficial outcomes.<\/p>\n<p>The study began as a project in Gratch\u2019s class, \u201cAffective Computing,\u201d which explores how algorithms can sense and respond to human emotion. In 2004, Gratch, a USC Viterbi research professor of computer science and psychology, co-developed EMA alongside Stacy Marsella, one of the first computational models to afford machines \u201cemotional intelligence.\u201d<\/p>\n<p>Gratch said that a personality-fluid AI agent that adapts to your way of speaking could soon open the door to much smoother human-AI interaction.<\/p>\n<p>\u201cYou might imagine another step is to create these agents that adapt to you as they learn more about you over time,\u201d Gratch said. \u201cThey can better align themselves, not just in terms of your needs, but also the way you want those needs communicated to yourself.\u201d<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-79746\" class=\"wp-image-79746 size-full\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2025\/09\/Overview.jpg\" alt=\"An example of how the virtual humans system developed by Bin Han works in practice (Photo\/Courtesy of Bin Han).\" width=\"1920\" height=\"1020\"  \/><\/p>\n<p id=\"caption-attachment-79746\" class=\"wp-caption-text\">An example of how the virtual humans system developed by Bin Han works in practice (Photo\/Courtesy of Bin Han).<\/p>\n<p>In this study, Han and her team focused on calibrating AI models to become more extroverted or introverted depending on the person it was interacting with. The goal was for the AI agent to match users\u2019 own personalities and conversational preferences so it can better interact with the user.<\/p>\n<p>\u201cI think a major domain that we can use this kind of technology is the mental health domain, because it\u2019s good to have a conversation when people feel depressed or a little blue,\u201d Han said. \u201cIf they want to share concerns, it would be good to share [with] a human-like thing, not only voice or text-based interaction.\u201d<\/p>\n<p>Other uses for these AI agents include the business world, where negotiation and conflict resolution are key to day-to-day operations. If people are nervous about a business decision or even negotiating a pay raise, it might be beneficial to test out their approach with an AI avatar, which could simulate a compatible conversation partner.<\/p>\n<p>\u201cIf we adopt a virtual agent system, then we can practice salary negotiation with a virtual agent, and we can [also] use it for strategy for a real-life company,\u201d Han said.<\/p>\n<p>This kind of simulation is already possible, and it will only get better as Han and her team continue to develop these models.<\/p>\n<p>AI, meet human emotion<\/p>\n<p>Han\u2019s decision to use extroversion as the sole personality trait to train these AI agents on was rooted in psychology, choosing just one trait for simplicity\u2019s sake to start. Extroversion is known in psychology as one of the \u201cbig five\u201d personality traits \u2014 alongside openness, conscientiousness, neuroticism and agreeableness \u2014 that are commonly used to understand people at a basic, predictable level.<\/p>\n<p>In an unrelated 2025 study at the University of Chicago, researchers found that <a href=\"https:\/\/www.npr.org\/2025\/07\/25\/nx-s1-5479044\/people-like-extroverted-robots-but-they-relate-to-the-neurotic-ones\" rel=\"nofollow noopener\" target=\"_blank\">\u201cpeople like extroverted robots \u2014 but they relate to the neurotic ones.\u201d<\/a><\/p>\n<p>Studying these traits \u2014 Han said she plans to examine the other four in the future \u2014 is a way to explore just how far these AI models can go. For her part, Han believes that AI can become significantly more socially and emotionally intelligent, to the point where it can give informed feedback to users daily.<\/p>\n<p>\u201cMy future works are going to contribute to make AI more socially intelligent, understand users\u2019<br \/>emotion better and give some thoughts or feedback about how to improve our daily life,\u201d Han said.<\/p>\n<p>Gratch believes that this project represents a step in expanding AI\u2019s potential.<\/p>\n<p>\u201cIt\u2019s part of a general trend to unpack and investigate just what [AI models] can and cannot do,\u201d Gratch said. \u201cWe\u2019re actually showing they understand not just text, but nonverbal communication around the general topic of social intelligence.\u201d<\/p>\n<p>Added Gratch: \u201cThere\u2019s research that [suggests that] things like personality matching are useful for influence,\u201d Gratch said. \u201cSo, if you want to persuade someone to take their medication or to buy a more expensive car, you adapt your style to the style of the person you\u2019re interacting with.\u201d<\/p>\n<p class=\"created-on\">Published on September 5th, 2025<\/p>\n<p class=\"last-updated\">Last updated on September 5th, 2025<\/p>\n","protected":false},"excerpt":{"rendered":"\u00a0 Bin Han developed a \u201cvirtual humans\u201d system focused on extroversion, due to be presented at the prominent&hellip;\n","protected":false},"author":2,"featured_media":138482,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[46],"tags":[191,74],"class_list":{"0":"post-138481","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-computing","8":"tag-computing","9":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/138481","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=138481"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/138481\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/138482"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=138481"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=138481"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=138481"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}