Derin öğrenme yöntemleri ve kelime yerleştirme modelleri kullanılarak Parkinson hastalığının duygu analiziyle değerlendirilmesi

Abstract

Parkinson hastalığı, hastanın yaşam kalitesini etkileyen, önemli sosyal ve ekonomik etkileri olan ve semptomların aşamalı görünümü nedeniyle erken teşhis edilmesi güç olan yaygın bir nörolojik hastalıktır. Parkinson hastalığının Twitter gibi sosyal medya platformlarında tartışılması, hastaların Parkinson hastalığının hem tanı hem de tedavi aşamasında birbirleriyle iletişim kurduğu bir platform sağlar. Bu çalışmanın amacı, derin öğrenme ve kelime yerleştirme modellerini kullanarak insanların Parkinson hastalığı ile ilgili duygu analizlerini değerlendirmek ve karşılaştırmaktır. Bildiğimiz kadarıyla, bu çalışma Parkinson hastalığını sosyal medya aracılığıyla kelime yerleştirme modelleri ve derin öğrenme algoritmaları kullanarak analiz etmek için yapılan ilk çalışmadır. Bu çalışmada, kelime yerleştirme modelleri olarak Word2Vec, GloVe ve FastText; Evrişimsel Sinir Ağları (CNN'ler), Tekrarlayan Sinir Ağları (RNN'ler) ve Uzun Kısa Süreli Bellek Ağları (LSTM'ler) derin öğrenme teknikleri olarak harmanlanmış ve sınıflandırma amacıyla kullanılmıştır. Kelime yerleştirme modelleri ve derin öğrenme algoritmaları kullanılarak Parkinson hastalığı hakkında kullanıcı yorumlarının duygularını analiz etmek amacıyla kapsamlı deneyler İngilizce Twitter veri kümesi üzerinde gerçekleştirilmiştir. Deney sonuçlarında, Word2Vec kelime yerleştirme modelinin CNN derin öğrenme algoritmasıyla harmanlanması sonucu %75.12 doğruluk ile kayda değer bir sınıflandırma başarısı gözlemlenmiştir. Bu çalışma, hastaların gereksinimlerini anlamak için kelime yerleştirme modelleri ve derin öğrenme algoritmalarını kullanma etkinliğini ve Parkinson hastalarının ve yakınlarının duygularını sosyal medya aracılığı ile analiz ederek tedavi sürecine değerli bir katkı sağladığını göstermektedir.

Keywords

• Parkinson hastalığı
• Duygu analizi
• Derin öğrenme modelleri
• Kelime yerleştirme yöntemleri

The evaluation of Parkinson's disease with sentiment analysis using deep learning methods and word embedding models

Abstract

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 through social media by using word embedding models and deep learning algorithms. In this study, Word2Vec, GloVe, and FastText as word embedding models and Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short Term Memory Networks (LSTMs) as deep learning techniques are blended and used for classification purpose. Extensive experiments are conducted to analyze the sentiments of user comments about Parkinson's disease using word embedding models and deep learning algorithms on English Twitter dataset. The remarkable classification success with 75.12% of accuracy is observed in the experiments through the result of blending Word2Vec as a word embedding model and CNN as a deep learning technique. This study demonstrates the effectiveness of using word embedding models and deep learning algorithms to understand patients' needs, and provides a valuable contribution to the treatment process by analyzing the feelings of Parkinson's patients and their relatives through social media.

Keywords

• Parkinson’s disease
• Sentiment analysis
• Deep learning models
• Word embedding methods

References

1. [1] Eckler P, Worsowicz G, Rayburn J. “Social media and healthcare: an overview”. Physical Medicine and Rehabilitation, 2(11), 1046-1050, 2010.
2. [2] Prieto VM, Matos S, Alvarez M, Cacheda F, Oliveira JL. “Twitter: A good place to detect health conditions”. Public Library of Science One, 9(1), 1-11, 2014.
3. [3] Sinnenberg L, Buttenheim AM, Padrez K, Mancheno C, Ungar L, Merchant RM. “Twitter as a tool for health research: A systematic review”. American Journal of Public Health, 107(1), 1-8, 2017.
4. [4] Neiger BL, Thackeray R, Burton SH, Thackeray CR, Reese JH. “Use of Twitter among local health departments: An analysis of information sharing, engagement, and action”. Journal of Medical Internet Research, 15(8), 1-10, 2013.
5. [5] Beykikhoshk A, Arandjelović O, Phung D, Venkatesh S, Caelli T. “Data-mining Twitter and the autism spectrum disorder: A pilot study”. IEEE/ACM 2014 International Conference on Advances in Social Networks Analysis and Mining, Beijing, China, 17-20 August 2014.
6. [6] Beykikhoshk A, Arandjelović O, Phung D, Venkatesh S. “Overcoming data scarcity of Twitter: Using tweets as bootstrap with application to autism-related topic content analysis”. IEEE/ACM 2015 International Conference on Advances in Social Networks Analysis and Mining, Paris, France, 25-28 August 2015.
7. [7] Chew C, Eysenbach G. “Pandemics in the age of Twitter: Content analysis of tweets during the 2009 H1N1 outbreak”. Public Library of Science One, 5(11), 1-13, 2010.
8. [8] DeRijk MD, Tzourio C, Breteler MM, Dartigues JF, Amaducci L, Lopez-Pousa S, Rocca WD. “Prevalence of parkinsonism and Parkinson's disease in Europe: The Europarkinson collaborative study. European community concerted action on the epidemiology of Parkinson's disease”. Journal of Neurology, Neurosurgery & Psychiatry, 62(1), 10-15, 1997.

9. [9] Fahn S. “Description of Parkinson's disease as a clinical syndrome”. Annals of the New York Academy of Sciences, 991, 1-14, 2003.
10. [10] Elman JL. “Finding structure in time”. Cognitive Science, 14(2), 179-211, 1990.
11. [11] Joulin A, Grave E, Bojanowski P, Douze M, Jégou H, Mikolov T. "Fasttext. zip: Compressing text classification models”. ICLR 2017 International Conference on Learning Representations, Toulon, France, 24-26 April, 2017.
12. [12] Kilimci ZH, Akyokuş S. “Deep learning-and word embedding based heterogeneous classifier ensembles for text classification”. Complexity, 2018, 106-116, 2018.
13. [13] Le Q, Mikolov T. “Distributed representations of sentences and documents”. International Conference on Machine Learning, Beijing, China, 21-26 June, 2014.
14. [14] Lipton ZC, Berkowitz J, Elkan C. “A critical review of recurrent neural networks for sequence learning”. https://arxiv.org/abs/1506.00019 (15.04.2019).
15. [15] Mikolov T, Chen K, Corrado G, Dean J. “Efficient estimation of word representations in vector space”. International Conference on Learning Representations Workshop, Scottsdale, Arizona, 2-4 May 2013.
16. [16] Pennington J, Socher R, Manning C. “Glove: Global vectors for word representation”. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25-29 October 2014.
17. [17] Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E. “Deep learning for computer vision: A brief review”. Computational Intelligence and Neuroscience, 2018, 130-143, 2018.
18. [18] Zhang L, Wang S, Liu B. “Deep learning for sentiment analysis: A survey”. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), 1-25, 2018.
19. [19] Ene M. “Neural network-based approach to discriminate healthy people from those with Parkinson's disease”. Annals of the University of Craiova-Mathematics and Computer Science Series, 35, 112-116, 2008.
20. [20] Little M, McSharry P, Hunter E, Spielman J, Ramig L. “Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease”. Nature Precedings, 1(1), 1-27, 2008.
21. [21] Sakar CO, Kursun O. “Telediagnosis of Parkinson’s disease using measurements of dysphonia”. Journal of Medical Systems, 34(4), 591-599, 2010.
22. [22] Das R. “A comparison of multiple classification methods for diagnosis of Parkinson disease”. Expert Systems with Applications, 37(2), 1568-1572, 2010.
23. [23] Çağlar MF, Çetişli B, Toprak İB. “Automatic recognition of Parkinson's disease from sustained phonation tests using ANN and adaptive neuro-fuzzy classifier”. Mühendislik Bilimleri ve Tasarım Dergisi, 1(2), 59-64, 2010.
24. [24] Polat K. “Classification of Parkinson's disease using feature weighting method on the basis of fuzzy c-means clustering”. International Journal of Systems Science, 43(4), 597-609, 2012.
25. [25] Luukka P. “Feature selection using fuzzy entropy measures with similarity classifier”. Expert Systems with Applications, 38(4), 4600-4607, 2011.
26. [26] Kihel BK, Benyettou M. “Parkinson’s disease recognition using artificial immune system”. Journal of Software Engineering and Applications, 4(7), 391-395, 2011.
27. [27] Eskidere Ö. “A Comparison of feature selection methods for diagnosis of Parkinson’s disease from vocal measurements”. Sigma, 30, 402-414, 2012.
28. [28] Prashanth R, Roy SD. “Novel and improved stage estimation in Parkinson's disease using clinical scales and machine learning”. Neurocomputing, 305, 78-103, 2018.
29. [29] Prashanth R, Roy SD. “Early detection of Parkinson’s disease through patient questionnaire and predictive modelling”. International Journal of Medical Informatics, 119, 75-87, 2018.
30. [30] Oscar N, Fox PA, Croucher R, Wernick R, Keune J, Hooker K. “Machine learning, sentiment analysis, and tweets: An examination of Alzheimer’s disease stigma on Twitter”. Journals of Gerontology Series B: Psychological Sciences and Social Sciences, 72(5), 742-751, 2017.
31. [31] Inan E, Soygazi F, Mostafapour V. “TurkiS: A Turkish sentiment analyzer using domain-specific automatic labelled dataset”. International Journal of Intelligent Systems and Applications in Engineering, 7(2), 99-103, 2019.
32. [32] Pervan N, Keleş Y. Derin Öğrenme Yaklaşımları Kullanarak Türkçe Metinlerden Anlamsal Çıkarım Yapma. Yüksek Lisans Tezi, Ankara Üniversitesi, Ankara, Türkiye, 2019.
33. [33] Krizhevsky A, Sutskever I, Hinton GE. “Imagenet classification with deep convolutional neural networks”. In Advances in Neural Information Processing Systems, Nevada, USA, 2-6 December 2012.
34. [34] Liu P, Qiu X, Huang X. “Adversarial multi-task learning for text classification”. Association for Computational Linguistics, Vancouver, Canada, 30 July- 4 August 2017.
35. [35] Loria S. “Textblob documentation”. https://buildmedia.readthedocs.org/media/pdf/textblob/latest/textblob.pdf (21.05.2019).
36. [36] Elman JL. “Finding structure in time”. Cognitive Science, 14(2), 179-211, 1990.
37. [37] Kilimci ZH, Akyokuş S, Omurca SI. “The effectiveness of homogenous ensemble classifiers for Turkish and English texts”. IEEE 2016 International Symposium on INnovations in Intelligent SysTems and Applications, Sinaia, Romania, 2-5 August 2016.
38. [38] Schneider KM. “On word frequency information and negative evidence in Naive Bayes text classification”. International Conference on Natural Language Processing, Alicante, Spain, 20-22 October 2004.
39. [39] Cevik F, Kilimci ZH. “Analysis of Parkinson’s disease using deep learning and word embedding models”. International Symposium on Innovative Technologies in Engineering and Science, Şanlıurfa, Turkey, 22-24 November 2019.
40. [40] Hutto CJ, Gilbert E. “Vader: A parsimonious rule-based model for sentiment analysis of social media text”. Eighth International AAAI Conference on Weblogs and Social Media, 27-29 May 2014.
41. [41] MonkeyLearn API Reference. https://monkeylearn.com/docs/article/api-reference/ (15.04.2020).