Parkinson disease analysis with deep learning and word embedding models

Objective Parkinson's disease is a common neurodegenerative neurological disorder, which affects the patient's quality of life, has significant social and economic effects, and is difficult to diagnose early due to the gradual appearance of symptoms. Examining the discussion of Parkinson's disease in social media platforms such as Twitter provides a platform where patients communicate each other in both diagnosis and treatment stage of the Parkinson's disease. The purpose of this work is to evaluate and compare the sentiment analysis of people about Parkinson's disease by using deep learning and word embedding models. To the best of our knowledge, this is the very first study to analyze Parkinson's disease from social media by using word embedding models and deep learning algorithms. Materials and Methods Tweets about Parkinson's disease are obtained by searching accounts on Twitter pages with keywords ("ParkinsonsCure", "Parkinson", "ParkinsonsTreatment, ParkinsonDiagnosis"). All tweets related to Parkinson's disease are collected from 01.01.2009 to 09.01.2019 using Selenium Crawler, which we write in Python programming language. In this study, Word2Vec, GloVe, and FastText are employed as word embedding models for the purpose of enriching tweets in terms of semantic, context, and syntax. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory Networks (LSTMs) are implemented for the classification task. Results In this study, extensive experiments are conducted to analyze the emotions of user comments about Parkinson's disease using word embedding models and deep learning algorithms. Accuracy is used as an evaluation metric in the experiments to demonstrate the classification performance of each model and the contribution of our study. When the effect of preprocessing methods on word embedding models is examined at 50% training set, it is observed that the combination of RH and RU methods shows the best accuracy performance. Word2Vec has the best results with 89.34% accuracy with preprocessing methods in word embedding models. Likewise, when the effect of preprocessing methods on deep learning algorithms is analyzed, it is observed that the consolidation of RH and RU gives better results than other preprocessing methods. LSTM is the best performing classification algorithm with 93.63% accuracy performance by blending with the RU + RH methods. Conclusions This study demonstrates the efficiency of using word embedding models and deep learning algorithms to understand the needs of patients' and provide a valuable contribution to the treatment process by analyzing sentiments of them.