Indiana University-Purdue University Indianapolis (IUPUI) / The aim of this research is to design a new method to identify the opioid use problems (OUP) among long-term opioid therapy patients in Indiana University Health using text mining and machine learning approaches. First, a systematic review was conducted to investigate the current variables, methods, and opioid problem definitions used in the literature. We identified 75 distinct variables in 9 models that majorly used ICD codes to identify the opioid problem (OUP). The review concluded that using ICD codes alone may not be enough to determine the real size of the opioid problem and more effort is needed to adopt other methods to understand the issue. Next, we developed a text mining approach to identify OUP and compared the results with the current conventional method of identifying OUP using ICD-9 codes. Following the institutional review board and an approval from the Regenstrief Institute, structured and unstructured data of 14,298 IUH patients were collected from the Indiana Network for Patient Care. Our text mining approach identified 127 opioid cases compared to 45 cases identified by ICD codes. We concluded that the text mining approach may be used successfully to identify OUP from patients clinical notes. Moreover, we developed a machine learning approach to identify OUP by analyzing patients’ clinical notes. Our model was able to classify positive OUP from clinical notes with a sensitivity of 88% on unseen data. We concluded that the machine learning approach may be used successfully to identify the opioid use problem from patients’ clinical notes. / 2019-06-21

Instalation which explore possibilities of visual language and poetry.

No description available.

No description available.

No description available.

No description available.

No description available.

Databases play a vital role in today's digital landscape, enabling effective data storage, management, and retrieval for businesses and other organizations. However, interacting with databases often requires knowledge of query (e.g., SQL) and analysis, which can be a barrier for many users. In natural language processing, the text-to-code task, which converts natural language text into query and analysis code, bridges this gap by allowing users to access and manipulate data using everyday language. This dissertation investigates different challenges in text-to-code (including text-to-SQL as a subtask), with a focus on four primary contributions to the field. As a solution to the lack of statistical analysis in current text-to-code tasks, we introduce SIGMA, a text-to-Code dataset with statistical analysis, featuring 6000 questions with Python code labels. Baseline models show promising results, indicating that our new task can support both statistical analysis and SQL queries simultaneously. Second, we present Ar-Spider, the first Arabic cross-domain text-to-SQL dataset that addresses multilingual limitations. We have conducted experiments with LGESQL and S²SQL models, enhanced by our Context Similarity Relationship (CSR) approach, which demonstrates competitive performance, reducing the performance gap between the Arabic and English text-to-SQL datasets. Third, we address context-dependent text-to-SQL task, often overlooked by current models. The SParC dataset was explored by utilizing different question representations and in-context learning prompt engineering techniques. Then, we propose GAT-SQL, an advanced prompt engineering approach that improves both zero-shot and in-context learning experiments. GAT-SQL sets new benchmarks in both SParC and CoSQL datasets. Finally, we introduce Ar-SParC, a context-dependent Arabic text-to-SQL dataset that enables users to interact with the model through a series of interrelated questions. In total, 40 experiments were conducted to investigate this dataset using various prompt engineering techniques, and a novel technique called GAT Corrector was developed, which significantly improved the performance of all baseline models.

In the field of Natural Language Processing, supervised machine learning is commonly used to solve classification tasks such as sentiment analysis and text categorization. The classical way of representing the text has been to use the well known Bag-Of-Words representation. However lately low-dimensional dense word vectors have come to dominate the input to state-of-the-art models. While few studies have made a fair comparison of the models' sensibility to the text representation, this thesis tries to fill that gap. We especially seek insight in the impact various unsupervised pre-trained vectors have on the performance. In addition, we take a closer look at the Random Indexing representation and try to optimize it jointly with the classification task. The results show that while low-dimensional pre-trained representations often have computational benefits and have also reported state-of-the-art performance, they do not necessarily outperform the classical representations in all cases.

How can I as a storyteller talk about humans and nature and the relation between us and the natural world? How can storytelling contribute to create interest and engagement in nature and the environment? In this project I have investigated different ways of talking about nature, climate and humans, trying to find a different voice and angle on this everlasting important theme. Through practical research I have tried different strategies, voices and moods, with the result being a very personal approach to nature and environmental anxiety in a short, dark, poetic film. / <p>The full thesis contains copyrighted material</p><p>which has been removed in the published version.</p>