Open Research Oklahoma

Recent Submissions

  • Item
    Improving freeze tolerance in putting green-type bermudagrasses through mowing height adjustments
    (Oklahoma Cooperative Extension Service, 2024-04) Xiang, Mingying; Moss, Justin Quetone
  • Item
    Managing squash bug populations through identification and control
    (Oklahoma Cooperative Extension Service, 2024-04) Lastovica, Parker; Dunn, Bruce; Mason, Tyler; Bonjour, Edmond
  • Item
    Balancing the books: A reflective analysis of my academic journey through Oklahoma State University’s School of Accounting
    (5/7/2024) Blumer, Sarah
    This thesis aims to provide a comprehensive and reflective exploration of my educational journey within the Oklahoma State University School of Accounting, emphasizing the crucial role played by active participation in student clubs and internships. This essay seeks to uncover the transformative effects of academics, extracurricular and experiential learning on my personal and professional development.
  • Item
    Analysis of body language in political communication
    (5/10/2024) Young, Seth
    Barring party identification, is the verbal message delivered by a political candidate our primary consideration when determining vote choice? Is it possible that the communicative techniques we evaluate in a conversational situation are parallel to our political evaluations? Given the significance of political positions, voters will place heightened consideration upon the verbal and non-verbal communication of a political candidate in an effort to better determine their capability to hold office, or evaluate the efficacy and/or morality of their proposed policies. The question being answered by this work is as follows; how do the non-verbal communicative techniques of a political candidate alter the vote choice of the electorate?
  • Item
    Investigation of multimodal aspect based sentiment analysis using a Crossmodal Model
    (5/3/2024) Williams, Jacob
    Multimodal aspect-based sentiment analysis, the task of identifying a target aspect and obtaining its sentiment, has begun to gain more and more attention in the natural language processing community. Although the field started with simply focusing on textual data, there are many datasets such as Twitter 2015 and 2017 that require models to apply both textual and visual focuses. In this work, the model we propose is the Cross Modal Model (CMM). This model contains a BERT model and a CNN, which extract textual and visual features from the dataset, then obtaining the attention on features, and finally concatenating the features together to obtain the sentiment prediction. We saw significant performance gains with this model that achieve breakthrough results on the Twitter 2015 and Twitter 2017 datasets. These results demonstrate how useful our method could be applied to other multimodal datasets and potentially other multimodal problems.

Communities in Open Research Oklahoma

Select a community to browse its collections.