Parkinson's Disease is a worldwide health problem, causing movement disorder and gait deficiencies. Automatic noninvasive techniques for Parkinson's disease diagnosis is appreciated by patients, clinicians and neuroscientists. Gait offers many advantages compared to other biometrics specifically when data is collected using wearable devices; data collection can be performed through inexpensive technologies, remotely, and continuously. In this study, a new set of gait features associated with Parkinson's Disease are introduced and extracted from accelerometer data. Then, we used a feature selection technique called maximum information gain minimum correlation (MIGMC). Using MIGMC, features are first reduced based on Information Gain method and then through Pearson correlation analysis and Tukey post-hoc multiple comparison test. The ability of several machine learning methods, including Support Vector Machine, Random Forest, AdaBoost, Bagging, and Naïve Bayes are investigated across different feature sets. Similarity Network analysis is also performed to validate our optimal feature set obtained using MIGMC technique. The effect of feature standardization is also investigated. Results indicates that standardization could improve all classifiers' performance. In addition, the feature set obtained using MIGMC provided the highest classification performance. It is shown that our results from Similarity Network analysis are consistent with our results from the classification task, emphasizing on the importance of choosing an optimal set of gait features to help objective assessment and automatic diagnosis of Parkinson's disease. Results illustrate that ensemble methods and specifically boosting classifiers had better performances than other classifiers. In summary, our preliminary results support the potential benefit of accelerometers as an objective tool for diagnostic purposes in PD.

No abstract

Cyberbullying is a major cyber issue that is common among adolescents. Recent reports show that more than one out of five students in the United States is a victim of cyberbullying. Majority of cyberbullying incidents occur on public social media platforms such as Twitter. Automated cyberbullying detection methods can help prevent cyberbullying before the harm is done on the victim. In this study, we analyze two corpora of cyberbullying tweets from similar incidents to construct and validate an automated detection model. Our method emphasizes the two claims that are supported by our results. First, despite other approaches that assume that cyberbullying instances use vulgar or profane words, we show that they do not necessarily contain negative words. Second, we highlight the importance of context and the characteristics of actors involved and their position in the network structure in detecting cyberbullying rather than only considering the textual content in our analysis.

No abstract

Cyberbullying is a major cyber issue that is common among adolescents. Recent reports show that more than one out of five students in the United States is a victim of cyberbullying. Majority of cyberbullying incidents occur on public social media platforms such as Twitter. Automated cyberbullying detection methods can help prevent cyberbullying before the harm is done on the victim. In this study, we analyze a corpus of cyberbullying Tweets to construct an automated detection model. Our method emphasizes on the two claims that are supported by our results. First, despite other approaches that assume that cyberbullying instances use vulgar or profane words, we show that they do not necessarily contain negative words. Second, we highlight the importance of context and the characteristics of actors involved and their position in the network structure in detecting cyberbullying rather than only considering the textual content in our analysis.