This project aims to incorporate the aspect of sentiment analysis into traditional stock analysis to enhance stock rating predictions by applying a reliance on the opinion of various stocks from the Internet. Headlines from eight major news publications and conversations from Yahoo! Finance’s “Conversations” feature were parsed through the Valence Aware Dictionary for Sentiment Reasoning (VADER) natural language processing package to determine numerical polarities which represented positivity or negativity for a given stock ticker. These generated polarities were paired with stock metrics typically observed by stock analysts as the feature set for a Logistic Regression machine learning model. The model was trained on roughly 1500 major stocks to determine a binary classification between a “Buy” or “Not Buy” rating for each stock, and the results of the model were inserted into the back-end of the Agora Web UI which emulates search engine behavior specifically for stocks found in NYSE and NASDAQ. The model reported an accuracy of 82.5% and for most major stocks, the model’s prediction correlated with stock analysts’ ratings. Given the volatility of the stock market and the propensity for hive-mind behavior in online forums, the performance of the Logistic Regression model would benefit from incorporating historical stock data and more sources of opinion to balance any subjectivity in the model.
This project features five new pieces for clarinet commissioned from three different composers including:
1. Rasa by Jeffrey Ouper
2. Faerie Tale Dances by Jeffrey Ouper
3. Amalgamated Widget by Tavia Sullens
4. Faerie Suite by Theresa Martin
5. Time Lapse by Theresa Martin
Faerie Suite and Amalgamated Widget are for unaccompanied clarinet; Time Lapse is a trio for clarinet, bass clarinet, and piano; Faerie Tale Dances is a trio for E-flat clarinet, sopranino recorder, and toy piano; and Rasa is a quartet for E-flat clarinet, two A clarinets, and bass clarinet. These pieces challenge the performer in various ways, including complex rhythm, use of extended techniques such as glissando, flutter tongue, and circular breathing, and synthetic and non-traditional scales. The composers were given guidelines prior to the compositional process to create works with a thematic connection to mythology, folklore, or fairy tales, and inspired by dance and non-western or traditional harmonies and idioms. This document offers background information about the composers and the works, and a performance guide is included for each. This guide provides recommendations and suggestions for each piece. Also included are interviews with each of the composers. Accompanying this document are recordings of each of the five pieces, performed by the author.
The first part of this study is a biographical sketch of Weill’s life and music. It is intended to provide context for the three songs by tracing his beginnings as a German composer of stage works with volatile political messages, to his flight to the United States and his emergence as a composer of Broadway successes.
The second part is a commentary on the composition of the three selected songs. The lyrics and musical content are examined to show how Weill’s settings convey the dramatic mood and meaning as well as the specific nuances of the words. Description of the context of these songs explains how they were textually and musically intended to advance the plot and the emotional arc of the dramatic characters. The popularity of these songs endures beyond their original shows, and so there is discussion of how other artists have adapted and performed them, and available recordings are cited.
Weill’s songs, his little masterpieces, have proven to be truly evocative and so attractive to American audiences that they have undergone myriad adaptations. This study seeks to provide the personal and historical background of Kurt Weill’s music and to demonstrate why these three songs in particular have proven to have such lasting appeal.