Interactive Visual Analytics for Knowledge Integration and Decision Intelligence

Permanent URI for this collectionhttps://hdl.handle.net/10125/109875

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item type: Item ,
    Tag Cloud Visualization Integrated with Dimensionality Reduction for Conceptualizing Communication Behavioral Data
    (2025-01-07) Yoo, Sangbong; Yoon, Chanyong; Seo, Seongbum; Lee, Hyelim; Kim, Jeong-Nam; Hong, Hyein; Jang, Yun
    Public relations (PR) aims to establish positive relationships of company-customer and government-citizen. PR researchers and scholars achieve this by analyzing communication behavioral data, which encompasses the public’s experiences in consumption, policy, and governance. However, labeling this data for analysis in PR is costly and complex, primarily due to its multi-label and the need for human judgment based on the Organization-Public Relationship Assessment (OPRA) concepts. Consequently, these problems limit the development of automated labeling models because more training data is needed for fine-tuning. In this paper, we propose a novel tag cloud visualization integrated with dimensionality reduction for conceptualizing communication behavioral data to address limitations in PR. We use attention-based embedding and dimensionality reduction to visualize the public’s experience as a scatter plot according to OPRA concepts. Additionally, we provide PR researchers and scholars with clues for multi-labeling by combining the tag cloud using Bag of Words (BoW) in a scatter plot. We evaluate our proposed interactive visualization through a case study and feedback from two PR researchers.
  • Thumbnail Image
    Item type: Item ,
    Leveraging Visual Analytics and Diverse Datasets for Proactive Pandemic Surveillance: A One Health Approach
    (2025-01-07) Basheer, Aseel; Jentner, Wolfgang; Ebert, David
    The primary objectives of this project are to use a variety of datasets and visual analytics methods to gain insights into and deal with any prospective pandemic. Our focus is on early detection and prompt public health actions, achieved by utilizing "One Health" data, comprising human, animal, and weather information, including geospatial data and Google Trends data. In this work, we created a Predictive Intelligence for Pandemic Prevention (PIPP) dashboard that contains interactive visualization techniques to simplify the information presented, making it easier for people to understand. Our main objectives include exploring the relationship among different types of One Health datasets, developing user-friendly interactive predictive/forecasting models coupled with visualization techniques, highlighting the significance of visual analytics techniques, and advocating for timely identification of potential pandemic threats. This integrated approach offers in-depth insights and supports informed decision-making in public health. We have also integrated several forecasting approaches to predict the trends of COVID-19 as a case study.
  • Thumbnail Image
    Item type: Item ,
    Visualizing Social Sentiment: Designing an Interactive Dashboard for Informed Decision-Making
    (2025-01-07) Borukhson, David; Glaum, Louisa; Weinhardt, Christof; Fegert, Jonas
    Amidst a polycrisis involving global health emergencies, climate change, and geopolitical conflicts, decision-makers face the challenge of discerning relevant and reliable social sentiment information from vast data streams. This study addresses the need for near real-time insights into public attitudes to support data-driven policy-making. Utilizing design science research, we present a qualitative study (n=19) for the development of meta-requirements for an interactive dashboard displaying social sentiment data. It is based on sentiments from over 26 million data points collected biweekly since November 2022 from representative panels in Germany and the US. Thereby, this research aims to create a Policy Advice Sentiment Dashboard (PASD) that informs decision-makers, emphasizing data quality and methodological rigor. We explore additional attributes required for impactful information and variations in informational preferences among different decision-making groups. Our findings guide the development of a prototypical PASD, addressing the critical need for effective data-driven decision-making in governmental contexts.
  • Thumbnail Image
    Item type: Item ,