[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127252-en":3,"doc-seo-127252-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},127252,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","A machine learning approach for predicting human shortest path task performance - Research overview","Finding a shortest path in a graph drawing is a key qualitative evaluation task in human-computer interaction research because better drawings lead to faster and more accurate search. This study presents a first machine learning framework to predict human performance, covering accuracy, response time, and mental effort, by learning from ground-truth shortest-path experiments. Correlated quality metrics and newly defined path faithfulness metrics are used to mitigate limited training data via transfer learning, and experiments confirm strong predictive capability with model MSP achieving an MSE of 0.7243.","| A machine learning approach for predicting human shortest path task performance\u003Cbr>Shijun Cai a ,∗, Seok-Hee Hong a , Xiaobo Xia a , Tongliang Liu a , Weidong Huang ba University of Sydney, Australia\u003Cbr>b University of Technology Sydney, Australia |  |  |\n| --- | --- | --- |\n| a r t i c l e i n f o |  | a b s t r a c t |\n| Article history:\u003Cbr>Available online 6 April 2022 |  | Finding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation of graph drawings. In this paper, we present the first machine learning approach to predict human shortest path task performance, including accuracy, response time, and mental effort.\u003Cbr>To predict the shortest path task performance, we utilize correlated quality metrics and the ground truth data from the shortest path experiments. Specifically, we introduce path faithfulness metrics and show strong correlations with the shortest path task performance. Moreover, to mitigate the problem of insufficient ground truth training data, we use the transfer learning method to pre-train our deep model, exploiting the correlated quality metrics.\u003Cbr>Experimental results using the ground truth human shortest path experiment data show that our models can successfully predict the shortest path task performance. In particular, model MSP achievesan MSE (i.e., test mean square error) of 0.7243 (i.e., data range from −17.27 to 1.81) for prediction.\u003Cbr>© 2022 The Authors. Published by Elsevier B.V. on behalf of Zhejiang University and Zhejiang University Press Co. Ltd. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)). |\n| Keywords:\u003Cbr>Graph drawing Machine learning\u003Cbr>Shortest path task Quality metrics |  |  |\n\n1. Introduction  \nEvaluation of graph drawings has been established as an important research area in graph drawing. Quality metrics (or aesthetic criteria), such as edge crossings, bends, area, total edge lengths, angular resolution and stress, have been proposed for quantitative evaluation of graph drawings (Di Battista et al., 1999). Subsequently, various graph drawing algorithms have been developed to optimize these metrics.  \nMoreover, qualitative evaluation on graph drawings is well studied using HCI (Human Computer Interaction) evaluation methods such as controlled human experiments. In particular, finding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation (Huang et al., 2008 ; Purchase, 1997 ; Ware et al., 2002). Namely, a drawing D1 of a graph is better than a drawing D2 , if human spend less time finding the shortest path with fewer errors.  \nA number of studies have established the correlation between quality metrics, such as edge crossings and crossing angles, and  \n∗ Corresponding author.  \nE-mail addresses: [scai5619@uni.sydney.edu.au](scai5619@uni.sydney.edu.au) (S. Cai), [seokhee.hong@sydney.edu.au](seokhee.hong@sydney.edu.au) (S.-H. Hong), [xxia5420@uni.sydney.edu.au](xxia5420@uni.sydney.edu.au)[ ](xxia5420@uni.sydney.edu.au)(X. Xia), [tongliang.liu@sydney.edu.au](tongliang.liu@sydney.edu.au) (T. Liu), [weidong.huang@uts.edu.au](weidong.huang@uts.edu.au)[ ](weidong.huang@uts.edu.au)(W. Huang).  \nthe shortest path task performance (i.e., time and accuracy). Specifically, Huang et al. (2016) defined the performance-based efficiency E of the shortest path task performance based on the accuracy, response time, and mental effort.  \nRecently, machine learning approaches have been used to address research problems in graph visualization, mainly focusing on quantitative evaluation (i.e., quality metrics) (Haleem et al., 2019 ; Kwon and Ma, 2019). More recently, a machine learning approach has been proposed to address qualitative evaluation, specifically predicting human preference task performance (Caiet al., 2021).  \nIn this paper, we present","cbCaicr1U07VyoHM","https://ap.wps.com/l/cbCaicr1U07VyoHM","pdf",1457629,1,12,"English","en",105,"# Introduction\n## Background on graph drawing evaluation\n## Quality metrics and qualitative human experiments\n## Prior work on machine learning for graph visualization\n# Method Overview\n## Path faithfulness metrics\n## Machine learning models and training setup\n# Experiments and Results\n## Predictive performance evaluation\n## Feature correlations and model MSP accuracy","[{\"question\":\"What human shortest path task performance metrics does the study predict?\",\"answer\":\"The study predicts efficiency-related performance, including accuracy, response time, and mental effort.\"},{\"question\":\"How are correlated quality metrics used in the prediction approach?\",\"answer\":\"Correlated quality metrics, together with ground-truth data from shortest path experiments, are leveraged as inputs, and path faithfulness metrics are introduced to capture relationships with performance.\"},{\"question\":\"How does the method address insufficient ground truth training data?\",\"answer\":\"Transfer learning is used to pre-train the deep model using information from correlated quality metrics before fine-tuning for shortest-path task performance prediction.\"}]","A machine learning approach for predicting human shortest path task performance - Research overview | PDF",1785937760,30,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-machine-learning-approach-for-predicting-human-shortest-path-task-performance-research-overview","",{"@graph":36,"@context":85},[37,54,68],{"@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/a-machine-learning-approach-for-predicting-human-shortest-path-task-performance-research-overview/127252/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What human shortest path task performance metrics does the study predict?","Question",{"text":75,"@type":76},"The study predicts efficiency-related performance, including accuracy, response time, and mental effort.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are correlated quality metrics used in the prediction approach?",{"text":80,"@type":76},"Correlated quality metrics, together with ground-truth data from shortest path experiments, are leveraged as inputs, and path faithfulness metrics are introduced to capture relationships with performance.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the method address insufficient ground truth training data?",{"text":84,"@type":76},"Transfer learning is used to pre-train the deep model using information from correlated quality metrics before fine-tuning for shortest-path task performance prediction.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]