Digital Commons Network^™

Towards Automated Domain-Oriented Lexicon Construction And Dimension Reduction For Arabic Sentiment Analysis, Hasan A. Alshahrani

Dissertations

Sentiment analysis is a type of text mining that uses Natural Language Processing (NLP) tools to identify and label opinionated text. There are two main approaches of sentiment analysis: lexicon-based, and statistical approach. In our research, we use the lexicon-based approach because the lexicon contains sentiment words and phrases which are the main linguistic units to express sentiments. More specifically, we work with domain-oriented lexicons as they are more efficient than general ones because the polarity is heavily driven by domains.

Arabic language has a degree of uniqueness that makes it hard to be processed with the available cross-language tools …

Spatio-Temporal Variability Of Precipitation And Drought In The State Of Arizona, Usa, Samuel Nimako Nyarkoh

Masters Theses

As a result of climate change, several dry regions continue to get drier as precipitation amounts decline. This decline impact water resources and hinder economic development. Understanding the variability of precipitation and drought through climatic, agricultural and hydrological studies is therefore critical to decision makers and stakeholders in developing proactive measures that promotes economic development.

This study therefore uses dataset from 55 Meteorological stations containing 110-year (1900-2010) monthly precipitation data and a series of spatial and temporal tests to investigate the spatial and temporal patterns of precipitation and drought as well as the effects of local factors such as topography …

Study Of Feasability For Phase Difference Extraction Using Software Defined Radio In Location Analysis, Paul Miller

Masters Theses

Here is a method for using the phase of an HF radio signal for use in location analysis. This computation is implemented in a software defined radio processing block in the GNU Radio environment. The signals analyzed are received by an Ettus Research USRP SDR. We created a phase analysis system called WMU Rootsync, which compares the roots of a received signal to the roots of a generated reference signal for the phase analysis. This research describes a prototype method for phase analysis only. Future projects may use these ideas differently than presented here. We intend for future projects to …