19916 research outputs found
Sort by
Battle on the Home Front: The Black USO on Requa Street 1942-1944
Get PDFThe intention of this paper is to explore what is currently known about the United Service Organizations (USOs) established for Black enlisted service members during the home front era of World War II (1941-1945). As USO locations provided recreational and support services for military personnel they simultaneously demonstrated steady resistance, resiliency, and agency facing segregation and discrimination. Through activism within the civic and community arenas, paired at times with civil disobedience and militancy, the USO support for Black enlisted members was secured. Though generally not well documented, this topic will concentrate on one USO for Black troops located in Indio, California on Requa Street in Southern California’s Inland Empire. While few resources illuminating this subject are available, primary source newspaper articles were relied upon extensively for Indio’s Requa Street USO as no formal historical submission to the national organization of the USO was found. These resources provide for analysis of designated USOs and Black troops roles, during an era of legislative protection for segregation. Broadening the legacy of Black troops’ military service to America defending democracy overseas while simultaneously fighting for a domestic victory stateside of freedoms for all Americans
The House Elena Built: Historical Archaeology of Las Violetas (CA-SDI-4674)
Get PDFLas Violetas, also known as the Dear Adobe, is a late 19th century structure in Escondido, California, that was nearly lost to history. Elena Couts Dear, her husband Parker, and their five sons lived on the property from 1895 to 1904, and it is Elena who will be the primary focus of this project. She grew up in a wealthy, well known family in San Diego County, and Parker Dear owned a large rancho in what is now Riverside County. However, their fortunes changed, and they settled in this small home and property, a stark contrast to the life they had before. The current property owner and a retired California State Parks historian began the research into the ownership of the property using available historical documents. However, there were gaps in the documented history. This project sought to fill some of these gaps using the archaeological record.
Because archaeological investigations had never been undertaken at Las Violetas, this project first sought to determine what artifacts were present at the site. From there, the artifact collection and analysis were guided by the following research questions in order to fill gaps in the historical information and find patterns in the artifacts that can tell us more about the people who lived there. The first question related to how the archaeological record expanded on the documented history of Las Violetas, the people who lived there, and this region of San Diego County. In particular, how did the archaeological record expand on what is known about Elena Dear, given her efforts to purchase the property and finish the house with her own money, and what did it reveal about her place in local society? The second question related to what the artifacts recovered during excavations revealed about transitions in the occupation of the adobe and/or in the socioeconomic status of the people who lived there. Specifically, what markers of status within the archaeological record indicated that the Dear family maintained or changed the lifestyle they enjoyed prior to their move to Las Violetas?
Through the lens of feminist theory at the household scale, I conducted artifact analyses to present a contextual interpretation centered on Elena Dear that considered the documented history at Las Violetas, along with the archaeological record. In addition, I used personal letters written by the Dears along with mentions of them in local newspapers to provide a more comprehensive picture of what their lives were like when they lived at Las Violetas. Although the historical documents ultimately provided more information about the lives of the Dears, the archaeological record from Las Violetas opens the door for a wide range of opportunities for future research
Bro Kenneth and others
No full textView of teenagers \u27Bro\u27 Kenneth, Cluade, Wilamea, Merlene, and Sueie in a house (black-and-white photograph).https://scholarworks.lib.csusb.edu/bridges-photographs/1332/thumbnail.jp
COMPARATIVE ASSESSMENT OF MACHINE LEARNING AND DEEP LEARNING MODELS FOR DRUG EFFECTIVENESS USING SENTIMENT ANALYSIS
Get PDFIn recent years, the proliferation of online patient-generated drug reviews has created a valuable resource for assessing drug effectiveness and patient satisfaction, with sentiment analysis emerging as a powerful tool for extracting insights from this unstructured data.
This culminating research project conducted a comparative analysis of traditional Machine Learning (ML) and Deep Learning (DL) models for assessing drug effectiveness using sentiment analysis of participant reviews. The research aimed to evaluate the performance of Support Vector Machine (SVM), XGBoost, Random Forest, Long Short-Term Memory (LSTM), and Bidirectional Encoder Representations from Transformers (BERT) models in this context. This culminating research project addressed three main research questions: (1) How do traditional ML models compare to each other in assessing drug effectiveness ratings? (2) How do DL models compare to each other in this assessment? (3) How do the performances of DL models compare to traditional ML methods? The data was sourced from UCI Machine Learning Repository and was analyzed using Python within the Kaggle environment.
Based on our analysis, for the first question, Random Forest demonstrated superior performance among traditional ML models, achieving 97% accuracy, followed by SVM (95%) and XGBoost (94%). Random Forest excelled in precision for negative reviews (0.99) and recall for positive reviews (0.99), while SVM and XGBoost showed slightly better precision for positive reviews (0.97). Regarding the second question, BERT outperformed LSTM in assessing drug effectiveness ratings. BERT achieved 86% accuracy compared to LSTM\u27s 82%. BERT demonstrated higher precision, especially for positive reviews (0.90), and better recall for negative reviews (0.68). BERT\u27s F1 scores were consistently higher than LSTM\u27s for both positive and negative reviews. Comparing traditional ML and DL models, the former, particularly Random Forest, outperformed DL models in overall accuracy, precision, recall and F1 score. However, DL models, especially BERT, showed promise in handling complex language patterns and nuances in sentiment analysis.
The study concludes that while traditional ML models, particularly Random Forest, currently offer superior performance in assessing drug effectiveness through sentiment analysis, DL models like BERT show potential for handling complex linguistic patterns. Future research directions include exploring multiclass classification, incorporating multimodal data, and investigating additional ML models for sentiment prediction. Using more recent and comprehensive datasets could provide current insights, while analyzing sentiment evolution over time for specific drugs or conditions may reveal valuable trends