A Visual Analytics Environment for Navigating Large Conceptual Models by Leveraging Generative Artificial Intelligence

被引:1
作者
Gandee, Tyler J. [1 ]
Glaze, Sean C. [1 ]
Giabbanelli, Philippe J. [1 ]
机构
[1] Miami Univ, Dept Comp Sci & Software Engn, Oxford, OH 45056 USA
关键词
causal map; details-on-demand; image generation; information overload; natural language generation;
D O I
10.3390/math12131946
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
While comprehensive knowledge networks can be instrumental in finding solutions to complex problems or supporting the development of detailed simulation models, their large number of nodes and edges can become a hindrance. When the representation of a network becomes opaque, they stop fulfilling their role as a shared representation of a system between participants and modelers; hence, participants are less engaged in the model-building process. Combating the information overload created by large conceptual models is not merely a matter of changing formats: shifting from an unwieldy diagram to enormous amounts of text does not promote engagement. Rather, we posit that participants need an environment that provides details on demand and where interactions with a model rely primarily on a familiar format (i.e., text). In this study, we developed a visual analytics environment where linked visualizations allow participants to interact with large conceptual models, as shown in a case study with hundreds of nodes and almost a thousand relationships. Our environment leverages several advances in generative AI to automatically transform (i) a conceptual model into detailed paragraphs, (ii) detailed text into an executive summary of a model, (iii) prompts about the model into a safe version that avoids sensitive topics, and (iv) a description of the model into a complementary illustration. By releasing our work open source along with a video of our case study, we encourage other modelers to use this approach with their participants. Their feedback and future usability studies are key to respond to the needs of participants by improving our environment given individual preferences, models, and application domains.
引用
收藏
页数:23
相关论文
共 79 条
  • [1] Akhavan A., 2023, Syst. Dyn. Rev, DOI [10.2139/ssrn.4675409, DOI 10.2139/SSRN.4675409]
  • [2] AlShaikh Fatema, 2021, 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), P403, DOI 10.1109/3ICT53449.2021.9582029
  • [3] Alshareef A., 2023, P INT C SIM TOOLS TE, P95
  • [4] [Anonymous], 2022, Suicide Prevention: Risk and Protective Factors
  • [5] Aperdannier Roman, 2024, Advances in Information and Communication: Proceedings of the 2024 Future of Information and Communication Conference (FICC). Lecture Notes in Networks and Systems (920), P526, DOI 10.1007/978-3-031-53963-3_36
  • [6] Apvrille Ludovic, 2024, P 12 INT C MOD BAS S, P27, DOI [10.5220/0012320100003645, DOI 10.5220/0012320100003645]
  • [7] Beltagy I, 2020, Arxiv, DOI arXiv:2004.05150
  • [8] Matrices, vector spaces, and information retrieval
    Berry, MW
    Drmac, Z
    Jessup, ER
    [J]. SIAM REVIEW, 1999, 41 (02) : 335 - 362
  • [9] Betker J., 2023, Improving image generation with better captions
  • [10] Birunda S. Selva, 2021, Innovative Data Communication Technologies and Application. Proceedings of ICIDCA 2020. Lecture Notes on Data Engineering and Communications Technologies (LNDECT 59), P267, DOI 10.1007/978-981-15-9651-3_23