Aaron Bowen

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 11
  • Item
    Multimodal combination of text and image tweets for disaster response assessment
    (CEUR-WS, 2022-07-06) Kotha, Saideshwar; Haridasan, Smitha; Rattani, Ajita; Bowen, Aaron; Rimmington, Glyn M.; Dutta, Atri
    Social media platforms are a vital source of information in times of natural and man-made disasters. People use social media to report updates about injured or dead people, infrastructure damage, missing or found people among other information. Studies show that social media data, if processed timely and effectively, could provide important insight to humanitarian organizations to plan relief activities. However, real-time analysis of social media data using machine learning algorithms poses multiple challenges and requires processing large amounts of labeled data. Multi-modal Twitter Datasets from Natural Disasters (CrisisMMD) is one of the dataset that provide annotations as well as textual and image data to help researchers develop a crisis response system. In this paper, we analyzed multi-modal data from CrisisMMD, related to seven major natural calamities like earthquakes, floods, hurricanes, wildfires, etc., and proposed an effective fusion-based decision making technique to classify social media data into Informative and Non-informative categories. The Informative tweets are then classified into various humanitarian categories such as rescue volunteering or donation efforts, not-humanitarian, infrastructure and utility damage, affected individuals, and other relevant information. The proposed multi-modal fusion methodology outperforms the text tweets-based baseline by 6.98% in the Informative category and 11.2% in the Humanitarian category, while it outperforms image tweets-based baselines by 4.5% in the Informative category and 6.39% in the humanitarian category
  • Item
    Adaptive scaffolding toward transdisciplinary collaboration: Reflective polyvocal self-study
    (Springer International Publishing, 2022-12-16) Alagic, Mara; Sclafani, Maria; Filbert, Nathan; Rimmington, Glyn; Demissie, Zelalem S.; Dutta, Atri; Bowen, Aaron; Lindsay, Ethan; Kuhlmann, Meghann; Rattani, Ajita; Rai, Atul
    Contemporary global challenges require experts from various disciplines to work together. Since every field of knowledge has its unique language and discipline-based culture, collaborative inquiry presents an additional challenge during such collaboration. Ideally, collaborators from each discipline can transcend their respective linguistic and cultural boundaries to achieve transdisciplinarity, where this includes sharing and taking perspectives, active listening; and adaptive, relational metacognitive scaffolding. Within such a framework, the merging of ideas, theories, research design, and methodologies can allow technological applications from each discipline to be achieved through active collaborative, sense-making, and sustained constructivist relations. Within the context of the Disaster Resilience Analytics Center (DRAC) research team, we developed a model of adaptive scaffolding via self-consistent, iterative refinement. This convergence project focused on socio-economic aspects, outreach, and STEAM education, along with postgraduate education. The research team comprised researchers from STEAM disciplines in physical sciences, mathematics, computer sciences, social sciences, humanities, education, and library science. It proved essential to occasionally step away from the research topic and to critically co-reflect on the initial and ongoing challenges in the convergence path. This resulted in more constructive integration and transcendence of disciplines, leading to the development of an adaptive scaffolding framework. We present this framework and additional reflective insights and limitations related to its potential application in different contexts.
  • Item
    Multimodal Combination of Text and Image Tweets for Disaster Response Assessment
    (International Workshop on Data-driven Resilience Research, 2022-07-06) Kotha, Saideshwar; Haridasan, Smitha; Rattani, Ajita; Bowen, Aaron; Rimmington, Glyn; Dutta, Atri
    Social media platforms are a vital source of information in times of natural and man-made disasters. People use social media to report updates about injured or dead people, infrastructure damage, missing or found people among other information. Studies show that social media data, if processed timely and effectively, could provide important insight to humanitarian organizations to plan relief activities. However, real-time analysis of social media data using machine learning algorithms poses multiple challenges and requires processing large amounts of labeled data. Multi-modal Twitter Datasets from Natural Disasters (CrisisMMD) is one of the dataset that provide annotations as well as textual and image data to help researchers develop a crisis response system. In this paper, we analyzed multi-modal data from CrisisMMD, related to seven major natural calamities like earthquakes, floods, hurricanes, wildfires, etc., and proposed an effective fusion-based decision making technique to classify social media data into Informative and Non-informative categories. The Informative tweets are then classified into various humanitarian categories such as rescue volunteering or donation efforts, not-humanitarian, infrastructure and utility damage, affected individuals, and other relevant information. The proposed multi-modal fusion methodology outperforms the text tweets-based baseline by 6.98% in the Informative category and 11.2% in the Humanitarian category, while it outperforms image tweets-based baselines by 4.5% in the Informative category and 6.39% in the humanitarian category.
  • Item
    A Review of Food Accessibility Measures and Decision Support Models
    (Wichita State University, 2022-06) Maldonado, Fransiera; Cure, Laila; Bowen, Aaron; Keene-Woods, Nikki; Rattani, Ajita; Hill, Twila; Lewis, Rhonda; Twomey, Janet
    The objective of this research is to identify quantitative methods to study food accessibility and investigate their use or potential in supporting decisions that improve our food systems. To achieve this objective, we reviewed peer-reviewed research articles explicitly describing a quantitative measure of food accessibility and/or individuals' experience of the food system.
  • Item
    Dispelling misinformation and disinformation about COVID-19 through a multidisciplinary teaching module
    (Wichita State University, 2021-04-08) Bowen, Aaron
    This presentation covered Aaron Bowen's strategies for designing a module for the Blackboard learning management system on how educators can fight the spread of mis- and disinformation regarding the COVID-19 pandemic.