[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127450-en":3,"doc-seo-127450-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127450,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","LISBET - a machine learning model for the automatic segmentation of social behavior motifs","Social behavior is essential for survival across many animal species, yet current studies often rely on interaction-time measurement or manual annotation of predefined behaviors. These approaches are time-consuming, biased by human labeling, and may miss subtle behavioral patterns. LISBET (LISBET Is a Social BEhavior Transformer) uses self-supervised learning from body tracking to automatically detect and segment social interactions without extensive annotation. Tested across multiple mouse datasets and scenarios, it supports classification, motif segmentation, and phenotyping, with neural signatures linked to discovered motifs.","1  \nLISBET: a machine learning model for the automatic segmentation of social behavior motifs  \nGiuseppe Chindemi* , Benoit Girard* and Camilla Bellone  \nDepartment of Basic Neurosciences, University of Geneva, Switzerland  \n*equal contribution  \nCorresponding authors: [camilla.bellone@unige.ch](camilla.bellone@unige.ch); giuseppe.chindemi@unige.ch  \nAbstract  \nSocial behavior is crucial for survival in many animal species, and a heavily investigated research subject. Current analysis methods generally rely on measuring animal interaction time or annotating predefined behaviors. However, these approaches are time consuming, human biased, and can fail to capture subtle behaviors.  \nHere we introduce LISBET ( LISBET Is a Social BEhavior Transformer) , a machine learning model for detecting and segmenting social interactions. Using self-supervised learning on body tracking data, our model eliminates the need for extensive human annotation.  \nWe tested LISBET in three scenarios across multiple datasets in mice: supervised behavior classification, unsupervised motifs segmentation, and unsupervised animal phenotyping. Additionally, in vivo electrophysiology revealed distinct neural signatures in the Ventral Tegmental Area corresponding to motifs identified by our model. In summary, LISBET automates data annotation and reduces human bias in social behavior research, offering a promising approach to enhance our understanding of behavior and its neural correlates.  \nIntroduction  \nAnimal behavior research has traditionally relied on human observers to categorize and label stereotypical movements or actions. While this approach has yielded valuable insights, it presents significant challenges that have long constrained the field. In particular, manual annotation of behaviors for quantitative research is often tedious, subjective, and prone to errors, potentially compromising the reliability and reproducibility of studies. Furthermore, the specific set of behaviors chosen for analysis in a study inherently introduces researcher bias, potentially limiting the scope of discoveries.  \nRecent advancements in machine learning methods within biological disciplines are addressing these challenges and revolutionizing behavioral research. These algorithmic approaches are enhancing our understanding of animal behavior in two important ways. On one hand, machine learning can replicate and automate human annotations through a hypothesis-driven approach, mitigating the issues of reproducibility and human error ( Bohnslav et al. , 2021; Marks et al. , 2022) . This application not only increases the efficiency of data analysis but also improves the consistency and reliability of behavioral classifications. On the other hand, these computational methods enable the discovery of new behavioral motifs through a data-driven approach, potentially revealing patterns that human observers might overlook (Wiltschko et al. , 2020 ; Dunn et al. , 2021; Hsu and Yttri, 2021; Luxem et al. , 2022) . This capability expands the breadth of behavioral investigations beyond preconceived notions,  \n2  \noffering opportunities to uncover previously unrecognized aspects of animal behavior. By leveraging these machine learning techniques, researchers can simultaneously enhance the efficiency and objectivity of behavioral analysis while also expanding the scope of their investigations.  \nHowever, despite the promising results obtained by these new tools in behavioral research, most progress in the field has been made in single-animal settings. Social interactions, characterized by the interplay of multiple individuals, introduce greater challenges that are not easily addressed by simply extending single-animal methods. While single-animal actions can be deconstructed into simple features like velocity (i.e. , locomotion) or body part positions (i.e. , rearing) , social interactions span multiple timescales and can be of extreme complexity (e.g. , group hunting) . Classification","cbCaiofn3VJ9qVT3","https://ap.wps.com/l/cbCaiofn3VJ9qVT3","pdf",4897439,1,25,"English","en",105,"# Abstract\n# Introduction\n## Limitations of manual annotation\n## Machine learning for behavioral analysis\n## Challenges of social interactions\n## Unsupervised methods and their gaps","[{\"question\":\"What problem does LISBET address in social behavior research?\",\"answer\":\"LISBET addresses the time-consuming, human-biased manual annotation and the inability of many approaches to capture subtle social behaviors.\"},{\"question\":\"How does LISBET detect and segment social interactions?\",\"answer\":\"LISBET uses self-supervised learning on body tracking data to eliminate the need for extensive human annotation while detecting and segmenting social interactions.\"},{\"question\":\"How was LISBET evaluated and what biological connection was found?\",\"answer\":\"LISBET was tested on multiple mouse datasets across supervised classification, unsupervised motif segmentation, and unsupervised animal phenotyping; in vivo electrophysiology showed distinct neural signatures in the Ventral Tegmental Area corresponding to motifs identified by the model.\"}]","LISBET - a machine learning model for the automatic segmentation of social behavior motifs | PDF",1785938931,63,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"lisbet-a-machine-learning-model-for-the-automatic-segmentation-of-social-behavior-motifs","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/lisbet-a-machine-learning-model-for-the-automatic-segmentation-of-social-behavior-motifs/127450/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does LISBET address in social behavior research?","Question",{"text":76,"@type":77},"LISBET addresses the time-consuming, human-biased manual annotation and the inability of many approaches to capture subtle social behaviors.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does LISBET detect and segment social interactions?",{"text":81,"@type":77},"LISBET uses self-supervised learning on body tracking data to eliminate the need for extensive human annotation while detecting and segmenting social interactions.",{"name":83,"@type":74,"acceptedAnswer":84},"How was LISBET evaluated and what biological connection was found?",{"text":85,"@type":77},"LISBET was tested on multiple mouse datasets across supervised classification, unsupervised motif segmentation, and unsupervised animal phenotyping; in vivo electrophysiology showed distinct neural signatures in the Ventral Tegmental Area corresponding to motifs identified by the model.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]