{"id":170876,"date":"2025-09-11T13:39:37","date_gmt":"2025-09-11T19:39:37","guid":{"rendered":"https:\/\/tecscience.tec.mx\/en\/?post_type=sciencecommunication&p=170876"},"modified":"2025-09-22T16:25:57","modified_gmt":"2025-09-22T22:25:57","slug":"artificial-intelligence-and-emotions","status":"publish","type":"sciencecommunication","link":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/","title":{"rendered":"RoBERTa vs. ChatGPT: Which One Understands Our Emotions Better?"},"content":{"rendered":"\n

By Diana Patricia Madera Esp\u00edndola<\/a>, Zo\u00e9 Caballero Dom\u00ednguez y Valeria Jassive Ram\u00edrez Mac\u00edas <\/strong>| AMATEUR SCIENCE<\/p>\n\n\n\n

Reviewing Author<\/em> H\u00e9ctor Gibr\u00e1n Ceballos Cancino<\/a><\/p>\n\n\n\n

Language is at the core of what makes us human. That\u2019s why so much effort has gone into teaching computers not only to recognize words, but also to grasp the meaning behind them.<\/p>\n\n\n\n

This field is called Natural Language Processing (NLP)<\/strong>, a branch of artificial intelligence that powers tools like Alexa and Siri, grammar autocorrect, spam filters, and\u2014more recently\u2014models like ChatGPT and Gemini.<\/p>\n\n\n\n

At the heart of advanced NLP systems lies Sentiment Analysis<\/strong><\/em>, which enables machines to go beyond processing text and start interpreting the emotions embedded in it<\/strong>. From flagging harmful social media posts to gauging public opinion on key topics, this technology is already influencing how we communicate and engage online.<\/p>\n\n\n\n

Emotions: an algorithmic challenge<\/h2>\n\n\n\n

Despite its wide range of applications, sentiment analysis still faces hurdles\u2014particularly when it comes to detecting complex emotions like hope<\/strong> or sarcasm<\/strong>.<\/p>\n\n\n\n

Hope is difficult to pin down because it involves layers of meaning. It can be expressed directly (\u201cI hope,\u201d \u201cI wish\u201d) or indirectly (\u201cMaybe things will change\u201d). Sarcasm is trickier still, playing with the gap between literal words and actual intent\u2014often positive-sounding phrases masking negative feelings.<\/p>\n\n\n\n

The ability to detect subtle emotions, such as hope or sarcasm, isn\u2019t just a technical milestone. It has real-world stakes, as seen during the pandemic, when a single post could signal either despair or encouragement.<\/p>\n\n\n\n

With the rise of generative AI, researchers are now examining how effectively these models can capture emotional nuance.<\/p>\n\n\n\n

At Tecnol\u00f3gico de Monterrey, a group of students set out to compare popular generative models\u2014ChatGPT, DeepSeek, Claude, and Llama<\/strong>\u2014against RoBERTa<\/strong>, a widely used pre-trained NLP model. Their focus was on identifying hope and sarcasm in Twitter posts across multiple languages.<\/p>\n\n\n\n

Their findings were accepted at two major international NLP conferences: RANLP<\/strong> and IBERLEF<\/strong>.<\/p>\n\n\n\n

Hope and sarcasm<\/h2>\n\n\n\n

In recent years, NLP techniques have made remarkable strides in their ability to detect emotions in text. One of the most well-known models is RoBERTa<\/strong>, a pre-trained model trained on millions of texts from books, articles, and social media.<\/p>\n\n\n\n

This extensive training adapts easily to new tasks, even with very little additional information. To better understand this, we can imagine a professional chef: even if they have never cooked a specific dish before, their experience allows them to prepare it perfectly with just a brief description.<\/p>\n\n\n\n

Generative models such as ChatGPT<\/strong> take this concept even further. They don\u2019t just understand language\u2014they produce it, simulating human conversations with remarkable fluency and contextual sensitivity. Rather than following a recipe, they are like improvisational chefs: they not only recognize the ingredients but can also create an entirely new dish according to the diner\u2019s preferences.<\/p>\n\n\n\n

Despite this, RoBERTa continues to outperform generative models in detecting emotions, which is notable given that newer models like ChatGPT are considered more advanced because they can not only understand language but also generate it fluently and naturally.<\/strong><\/p>\n\n\n\n

This may be because generative models rely more heavily on message context, which can hinder their performance on Twitter posts that consist of very few characters.<\/p>\n\n\n\n

Models like RoBERTa have become widely used in the research community for emotion detection tasks. One of their key advantages is that they are not limited to English\u2014the most common language in research\u2014but can also adapt to other languages.<\/p>\n\n\n\n

This is particularly important in a globalized world, where emotions are expressed depending on language and culture. Using models capable of understanding multiple languages allows for the development of more inclusive and effective tools for people in diverse contexts.<\/p>\n\n\n\n

Although generative models like ChatGPT do not yet perform best in sentiment analysis tasks, studying their behavior remains essential\u2014especially given their widespread use today.<\/p>\n\n\n\n

Pursuing this line of research is not just a technical achievement\u2014it\u2019s a step toward a more empathetic future. Enhancing machines\u2019 ability to recognize complex emotions could unlock applications with deep social impact: from early detection of mental health challenges to better customer service, stronger safeguards against hate speech, and more human-like interactions between people and intelligent systems.<\/p>\n\n\n\n

.<\/p>\n\n\n\n

References<\/strong><\/h4>\n\n\n\n
    \n
  1. Madera-Esp\u00edndola, D. P., Caballero-Dom\u00ednguez, Z., Ram\u00edrez-Mac\u00edas, V. J., Butt, S., & Ceballos, H. (2025). Transformers and Large Language Models for Hope Speech Detection: A Multilingual Approach for PolyHope-M at RANLP 2025. Proceedings of the 16th International Conference on Recent Advances in Natural Language Processing.<\/em><\/li>\n\n\n\n
  2. Madera-Esp\u00edndola, D. P., Caballero-Dom\u00ednguez, Z., Ram\u00edrez-Mac\u00edas, V. J., Butt, S., & Ceballos, H. (2025). Hope Speech Detection Using Transformers and Large Language Models: A Bilingual Approach at IberLEF 2025. CEUR Workshop Proceedings.<\/em><\/li>\n\n\n\n
  3. Jim, J. R., Talukder, M. A. R., Malakar, P., Kabir, M. M., Nur, K., & Mridha, M. F. (2024). Recent advancements and challenges of NLP-based sentiment analysis: A state-of-the-art review<\/a>. Natural Language Processing Journal<\/em>, 6<\/em>.<\/li>\n<\/ol>\n\n\n\n

    .<\/p>\n\n\n\n

    Autoras<\/h4>\n\n\n\n

    Diana Patricia Madera Esp\u00edndola<\/a>.<\/strong> Graduate student in the Master\u2019s program in Computational Sciences at Tecnol\u00f3gico de Monterrey. Research assistant at the Living Lab & Data Hub of the Institute for the Future of Education (IFE), Tecnol\u00f3gico de Monterrey, Mexico. Her work at IFE focuses on projects related to Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning techniques.<\/p>\n\n\n\n

    Zo\u00e9 Caballero Dom\u00ednguez. <\/strong>Graduate student in the Master\u2019s program in Computer Science with a specialization in Machine Learning at Tecnol\u00f3gico de Monterrey.<\/p>\n\n\n\n

    Valeria Jassive Ram\u00edrez Mac\u00edas<\/strong>. Graduate student in the Master\u2019s program in Computational Sciences at Tecnol\u00f3gico de Monterrey.<\/p>\n\n\n\n

    .<\/p>\n\n\n\n


    This article was supervised by     H\u00e9ctor Gibr\u00e1n Ceballos Cancino<\/a>, director of the Living Lab & Data Hub<\/a> of the Institute for the Future of Education<\/a> (IFE) at Tecnol\u00f3gico de Monterrey. Full-time faculty member of the Graduate Program in Computer Science (DCC) and affiliated with the Research Group with Strategic Focus on Intelligent Systems. Member of the Mexican National System of Researchers (SNI) and an adherent member of the Mexican Academy of Computing (AMEXCOMP).<\/em><\/p>\n\n\n\n

    <\/p>\n","protected":false},"excerpt":{"rendered":"

    Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.<\/p>\n","protected":false},"author":18,"featured_media":170877,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_eb_attr":"","footnotes":""},"categories":[558],"tags":[234],"class_list":["post-170876","sciencecommunication","type-sciencecommunication","status-publish","format-standard","has-post-thumbnail","hentry","category-education-and-humanism","tag-institute-for-the-future-of-education"],"acf":[],"yoast_head":"\nHope and Sarcasm: A Challenge for Algorithms | TecScience<\/title>\n<meta name=\"description\" content=\"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"RoBERTa vs. ChatGPT: Which One Understands Our Emotions Better?\" \/>\n<meta property=\"og:description\" content=\"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/\" \/>\n<meta property=\"og:site_name\" content=\"TecScience\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-22T22:25:57+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2025\/09\/artificial-intelligence-and-emotions.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"750\" \/>\n\t<meta property=\"og:image:height\" content=\"500\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/\",\"url\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/\",\"name\":\"Hope and Sarcasm: A Challenge for Algorithms | TecScience\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/9\\\/2025\\\/09\\\/artificial-intelligence-and-emotions.jpg\",\"datePublished\":\"2025-09-11T19:39:37+00:00\",\"dateModified\":\"2025-09-22T22:25:57+00:00\",\"description\":\"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/#primaryimage\",\"url\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/9\\\/2025\\\/09\\\/artificial-intelligence-and-emotions.jpg\",\"contentUrl\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/9\\\/2025\\\/09\\\/artificial-intelligence-and-emotions.jpg\",\"width\":750,\"height\":500,\"caption\":\"Machine learning technology still faces a challenge: recognizing complex emotions like hope and sarcasm. Photo: Getty Images\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/artificial-intelligence-and-emotions\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Science Communication\",\"item\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/science-communication\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"RoBERTa vs. ChatGPT: Which One Understands Our Emotions Better?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/\",\"name\":\"TecScience\",\"description\":\"-\",\"publisher\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#organization\",\"name\":\"TecScience\",\"url\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/9\\\/2022\\\/11\\\/logo-negro-tecscience.svg\",\"contentUrl\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/9\\\/2022\\\/11\\\/logo-negro-tecscience.svg\",\"width\":250,\"height\":38,\"caption\":\"TecScience\"},\"image\":{\"@id\":\"https:\\\/\\\/tecscience.tec.mx\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Hope and Sarcasm: A Challenge for Algorithms | TecScience","description":"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/","og_locale":"en_US","og_type":"article","og_title":"RoBERTa vs. ChatGPT: Which One Understands Our Emotions Better?","og_description":"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.","og_url":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/","og_site_name":"TecScience","article_modified_time":"2025-09-22T22:25:57+00:00","og_image":[{"width":750,"height":500,"url":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2025\/09\/artificial-intelligence-and-emotions.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/","url":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/","name":"Hope and Sarcasm: A Challenge for Algorithms | TecScience","isPartOf":{"@id":"https:\/\/tecscience.tec.mx\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/#primaryimage"},"image":{"@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/#primaryimage"},"thumbnailUrl":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2025\/09\/artificial-intelligence-and-emotions.jpg","datePublished":"2025-09-11T19:39:37+00:00","dateModified":"2025-09-22T22:25:57+00:00","description":"Tec de Monterrey students conducted a study on how AI Models detect emotions on Twitter, focusing on subtle feelings.","breadcrumb":{"@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/#primaryimage","url":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2025\/09\/artificial-intelligence-and-emotions.jpg","contentUrl":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2025\/09\/artificial-intelligence-and-emotions.jpg","width":750,"height":500,"caption":"Machine learning technology still faces a challenge: recognizing complex emotions like hope and sarcasm. Photo: Getty Images"},{"@type":"BreadcrumbList","@id":"https:\/\/tecscience.tec.mx\/en\/science-communication\/artificial-intelligence-and-emotions\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/tecscience.tec.mx\/en\/"},{"@type":"ListItem","position":2,"name":"Science Communication","item":"https:\/\/tecscience.tec.mx\/en\/science-communication\/"},{"@type":"ListItem","position":3,"name":"RoBERTa vs. ChatGPT: Which One Understands Our Emotions Better?"}]},{"@type":"WebSite","@id":"https:\/\/tecscience.tec.mx\/en\/#website","url":"https:\/\/tecscience.tec.mx\/en\/","name":"TecScience","description":"-","publisher":{"@id":"https:\/\/tecscience.tec.mx\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/tecscience.tec.mx\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/tecscience.tec.mx\/en\/#organization","name":"TecScience","url":"https:\/\/tecscience.tec.mx\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/tecscience.tec.mx\/en\/#\/schema\/logo\/image\/","url":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2022\/11\/logo-negro-tecscience.svg","contentUrl":"https:\/\/tecscience.tec.mx\/en\/wp-content\/uploads\/sites\/9\/2022\/11\/logo-negro-tecscience.svg","width":250,"height":38,"caption":"TecScience"},"image":{"@id":"https:\/\/tecscience.tec.mx\/en\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/sciencecommunication\/170876","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/sciencecommunication"}],"about":[{"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/types\/sciencecommunication"}],"author":[{"embeddable":true,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/users\/18"}],"replies":[{"embeddable":true,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/comments?post=170876"}],"version-history":[{"count":0,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/sciencecommunication\/170876\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/media\/170877"}],"wp:attachment":[{"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/media?parent=170876"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/categories?post=170876"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tecscience.tec.mx\/en\/wp-json\/wp\/v2\/tags?post=170876"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}