Overview and details of the sessions of this conference. Please select a date or room to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
This agenda is preliminary and subject to change.
Please note that all times are shown in the time zone of the conference. The current conference time is: 19th May 2024, 09:08:56pm CST
Session Chair: Chang Liu, Peking University Session Chair: Jing Zhang, Sun Yat-sen University
Location:Room 4
Events III on 3F
3F沙龙III
Presentations
Research on influencing factors of medical data sharing among medical institutions based on SD model
M. Zhang1, D. Mu1,2, J. Deng3
1School of Public Health, Jilin University; 2The First Hospital of Jilin University; 3School of Business and Management, Jilin University
[Purpose/Significance] This paper aims to reveal the dynamic evolution trend of medical data sharing system and its influencing factors, so as to improve the research depth of medical data sharing and provide important basis and suggestions for medical data sharing.[Method/Process] According to the theory of planning behavior and social capital, the key factors affecting medical data sharing are explored, and the system dynamic model of medical data sharing among medical institutions is constructed, and the medical data sharing is simulated and predicted.[Results/Conclusions] The influence degree of various factors in the early stage of medical data sharing is as follows: organization sharing environment> sharing platform = data resources> institutional guarantee> individual willingness to share, and individual willingness to share grows fastest throughout the simulation cycle. Healthcare data sharing is more affected by the expected benefits than the shared costs in the early stage, and vice versa in the later stages. Laws affect healthcare data sharing more than policy and funding. In the later stage of medical data sharing, the lack of data resources and sharing platforms seriously reduced the level of medical data sharing.
Influence of Information Frames, Reference Points on Willingness to Accept Green Agricultural Production: Evidence from an Eye-Movement Experiment
F. Li1, C. Qin1, H. Lei2, X. Ma1
1School of Economics and Management, Xidian University; 2International Business School, Shaanxi Normal University
Low willingness to accept green agricultural production slows down the restoration of ecological badlands. Effective advertising message interventions can improve farmers' attitudes. Eye-tracking methodology was used to explore the effects of message frames (positive vs. negative frames) and reference points (self-reference vs. others' reference) on farmers' willingness to accept green agricultural production and the mediating role of attention in it. A total of 81 microdata from the field experiment were generated. The results of the study showed that positively framed information was more attended to by farmers than negatively framed information, and that positively framed information had a greater facilitating effect on farmers' acceptance. There was no significant difference in attention between self-referential and others' reference point information. The two-way ANOVA of information frames and reference points on attention and acceptance indicated that people paid more attention and had stronger acceptance in the positive frames of others' reference points. Individual's attention time and number of gaze played a mediating role in the path of information frames, positively affecting farmers' willingness to accept. The results of this study provide guidance for the development of information dissemination strategies for the application of green agricultural production technologies in rural areas.
TCMKS:基于知识图谱的中草药-疾病知识智能问答系统
豆. 赵1, 治. 欧1, 嘉. 曾1, 蕤. 刘1, 昶. 刘2
1赵豆豆、欧治毅、曾嘉怡、刘蕤*(*通讯作者),Central China Normal University, School of Information Management,Wuhan 430079; 2刘昶*(*通讯作者),Chinese Academy of Medical Sciences, Institute of Medicinal Plant Development, Beijing 100193
中医药知识中包含大量高度关联的数据,如何有效地组织这些复杂数据并挖掘其中隐藏的关系一直是亟待解决的问题。在本研究中,我们构建了TCMKS(Traditional Chinese Medicine Knowledge System)来管理、发现和利用中医药知识。系统包括10种实体类型(其中499种草药、452种植物、175,633种化合物、13,183种疾病、586,153种基因、1,907种miRNA、2,567条信号传导通路、9,693种症状、15,449种成分和46,160种方剂)、848,604个中西医学概念和222,396,210条关系,数据量超过了其他同类信息系统。TCMKS使用Neo4j存储数据并使用Django构建知识系统的前端交互界面。TCMKS支持中医药信息浏览、基于自然语言的智能查询、实体查询以及基于知识图谱的多跳关系查询等系统功能。TCMKS还将miRNA纳入其中,方便查询方剂-miRNA-疾病和草药-miRNA-疾病关系,有助于了解miRNA在疾病中的作用,促进开发涉及特定miRNA的新疗法。此外,本文对TCMKS进行了系统测评,其问答方法在评测中准确率达到了81.7%。通过对比TCMKS与通用生成式人工智能ChatGPT 3.5及领域生成式人工智能“数智岐黄”回答领域问题的效果,表明TCMKS具备更好的准确性和全面性。TCMKS在药物筛选、药理评估和药物开发方面的应用使其成为药用植物研究中不可或缺的资源。
为教育游戏用户创造心流体验:提升学习表现和满意度
Z. Sun1, T. Jiang1,2, Y. Xu1, P. Chen1
1School of Information Management, Wuhan University, Wuhan, Hubei, China; 2Center for Studies of Information Resources, Wuhan University, Wuhan, Hubei, China