[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291075-105":59,"doc-detail-291075-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","advanced-machine-learning-techniques-for-social-support-detection-on-social-media","Advanced Machine Learning Techniques for Social Support Detection on Social Media","","Widespread use of social media has intensified interest in how online social support influences user wellbeing. This study leverages a social-support-focused dataset and formulates the task as three classification problems: supportive versus non-supportive, support aimed at an individual versus a group, and the specific support type spanning categories such as Nation, LGBTQ, Black people, Women, Religion, and Other. To mitigate data imbalance, K-means clustering is used and compared to the original distribution. Transformer-based models outperform baselines, with reported improvements of 0.4% macro F1 for task two and 0.7% for task three versus prior TF-IDF-driven methods.",{"@graph":69,"@context":122},[70,84,105],{"@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/advanced-machine-learning-techniques-for-social-support-detection-on-social-media/291075/",{"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/advanced-machine-learning-techniques-for-social-support-detection-on-social-media/291075.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How is social support classification structured in this study?","Question",{"text":112,"@type":113},"The study divides the problem into three tasks: distinguishing supportive vs. non-supportive content, identifying whether support targets an individual or a group, and classifying the support type into categories such as Nation, LGBTQ, Black people, Women, Religion, and Other.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What method is used to address data imbalance?",{"text":117,"@type":113},"K-means clustering is employed to balance the dataset, and its results are compared against the original unbalanced data.",{"name":119,"@type":110,"acceptedAnswer":120},"Which machine learning approaches show the best performance?",{"text":121,"@type":113},"Transformer-based methods, including transformers and zero-shot learning with GPT-3, GPT-4, and GPT-4-o, demonstrate superior performance to baseline models across learning approaches.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},291075,1789643383,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":46,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","Advanced Machine Learning Techniques for Social Support Detection on Social Media  \nOlga Kolesnikovaa, ∗, Moein Shahiki Tasha, ∗, Zahra Ahania, Ameeta Agrawalb, Rau´l Monroyc, Grigori Sidorova  \naInstituto Polite´cnico Nacional (IPN), Centro de Investigacio´n en Computacio´n (CIC), Mexico City, Mexico,  \nbDepartment of Computer Science, Portland State University, USA,  \ncTecnologico de Monterrey Escuela deIngenieria y Ciencias  \nAbstract  \nThe widespread use of social media highlights the need to understand its impact, particularly the role of online social support. This study uses a dataset focused on online social support, which includes binary and multiclass classifications of social support content on social media. The classification of social support is divided into three tasks. The first task focuses on distinguishing between supportive and non-supportive. The second task aims to identify whether the support is directed toward an individual or a group. The third task categorizes the specific type of social support, grouping it into categories such as Nation, LGBTQ, Black people, Women, Religion, and Other (if it does not fit into the previously mentioned categories) . To address data imbalances in these tasks, we employed K-means clustering for balancing the dataset and compared the results with the original unbalanced data. Using advanced machine learning techniques, including transformers and zero-shot learning approaches with GPT3, GPT4, and GPT4-o, we predict social support levels in various contexts. The effectiveness of the dataset is evaluated using baseline models across different learning approaches, with transformer-based methods demonstrating superior performance. Additionally, we achieved a 0.4% increase in the macro F1 score for the second task and a 0.7% increase for the third task, compared to previous work utilizing traditional machine learning with psycholinguistic and unigram-based TF-IDF values.  \nKeywords: Social Support Detection, Social Media, GPT, Zero-Shot Learning  \n1. Introduction  \nPlatforms such as YouTube, Instagram, Snapchat, TikTok, and Facebook have become integral to daily life worldwide (Statista, 2024) . These platforms allow users to observe and interact with others, obtaining social rewards (Meshi et al., 2015) that act as reinforcers, bringing people back to these sites repeatedly and for substantial durations (Stewart, 2016) . However, problematic social media use has been consistently linked to negative mental health outcomes. A meta-analysis concluded that greater problematic Facebook use is associated with higher levels of depression and anxiety (Marino et al., 2018) . Another recent meta-analysis, which focused on problematic use across any social media platform, found similar associations, indicating that greater problematic social media use correlates with increased depression, anxiety, and loneliness (Huang, 2022) .  \nOne potential mechanism for mediating this relationship could be the amount of social support an individual receives. Researchers have speculated that more time on social media leads to a lack of face-to-face social interaction and that this lack of in-person social support may be responsible for the association between problematic social media use and negative mental health (Shensa et al., 2017) . Indeed, more time spent on social media has been associated with less perceived real-life social support (McDougall et al., 2016) .  \nDespite these findings, more comprehensive data and an understanding of the complex relationship between social media  \n∗ These authors contributed equally to this work.  \nuse and mental health is still needed. To address this gap (Ahaniet al., 2024b) have introduced a new dataset focused on online social support. Online social support involves behaviors, communication, and interactions that demonstrate care and appreciation for individuals, thus fostering a sense of belonging and helping to cope with life’s challenges (Ko et al., 2013)","cbCaimxWiK3nN4Cp","https://ap.wps.com/l/cbCaimxWiK3nN4Cp","pdf",716773,"English","# Introduction\n## Social media, problematic use, and mental health\n## Social support as a mediating mechanism\n## Existing datasets and research gap\n## Overview of the proposed approach\n# Transformer foundations\n## BERT and GPT models","[{\"question\":\"How is social support classification structured in this study?\",\"answer\":\"The study divides the problem into three tasks: distinguishing supportive vs. non-supportive content, identifying whether support targets an individual or a group, and classifying the support type into categories such as Nation, LGBTQ, Black people, Women, Religion, and Other.\"},{\"question\":\"What method is used to address data imbalance?\",\"answer\":\"K-means clustering is employed to balance the dataset, and its results are compared against the original unbalanced data.\"},{\"question\":\"Which machine learning approaches show the best performance?\",\"answer\":\"Transformer-based methods, including transformers and zero-shot learning with GPT-3, GPT-4, and GPT-4-o, demonstrate superior performance to baseline models across learning approaches.\"}]","Advanced Machine Learning Techniques for Social Support Detection on Social Media | PDF"]