Detecting Personal Health Data Disclosures in Turkish Social Data

Abstract

The number of users of social networking environments is increasing day by day. In parallel with the number of users, new social networking platforms are also taking place on the internet according to the wishes and needs of the users. Social networking environments, which are in an indispensable position with the instinct of socialization, also provide an environment for unconscious personal data disclosures. In this study, the health data disclosed by users in social networks due to lack of awareness has been focused on. By using the data collected from Twitter, it is aimed to identify the tweets that disclose health data. To achieve this purpose tweets collected from Twitter in accordance with search keywords about personal health experiences and annotated by a group of computer engineers. Created corpus preprocessed with natural language processing tool for Turkic languages, named Zemberek, and classified with Fasttext library. With language model created, tweets containing personal health data disclosure were detected with %88 accuracy. The main contributions in this paper are mainly; being the first study to detect personal health data disclosures in Turkish language, creation of Turkish search keywords that will serve as a reference for obtaining data to meet the health data domain, instead of disease-specific approach seen frequently in literature a holistic perspective implemented by collecting tweets containing many distinct keywords about health experiences, and creation of Turkish data corpus by manually annotating around 4.500 tweets in personal health data domain.

Keywords

• health data
• disclosure
• privacy
• social network
• social data
• personal data

References

1. S. Kemp, “Digital 2021 global overview report,” Accessed May. 01, 2022, 2021. [Online]. Avail- able: https://wearesocial- cn.s3.cn- north- 1.amazonaws.com.cn/ common/digital2021/digital-2021-global.pdf
2. M. Timothy, F. Theodore, and S. Allison. Customer data: Designing for transparency and trust. Accessed May. 01, 2022. [Online]. Available: https://www.hipaajournal.com/ december-2021-healthcare-data-breach-report/
3. C. Zhang, J. Sun, X. Zhu, and Y. Fang, “Privacy and security for online social networks: Challenges and opportunities,” IEEE Network, vol. 24, no. 4, pp. 13–18, 2010.
4. S. E. Erol and S. Sagiroglu, “Privacy awareness in social networks,” in 2021 International Conference on Information Security and Cryptology (ISCTURKEY), 2021, pp. 57–62.
5. “Cost of a data breach report,” Accessed May. 01, 2022, 2021. [Online]. Available: https://www.ibm.com/downloads/ cas/OJDVQGRY
6. S. Alder. December 2021 healthcare data breach report. Accessed May. 01, 2022. [Online]. Available: https://www.hipaajournal.com/ december-2021-healthcare-data-breach-report/
7. I. Lella, M. Theocharidou, E. Tsekmezoglou, and A. Malatras, “Enisa threat lanscape 2021,” Accessed May. 01, 2022, 2021. [Online]. Available: https://www.enisa.europa.eu/publications/ enisa-threat-landscape-2021.
8. “Kamuoyu duyurusu (Veri ihlali bildirimi) – Yonca Sağlık Hizmetleri Ltd. Şti.” Accessed May. 01, 2022. [Online]. Available: https://www.kvkk.gov.tr/Icerik/7199/ Kamuoyu-Duyurusu-Veri-Ihlali-Bildirimi-Yonca-Saglik-Hizmetleri-Ltd-Sti-

9. “Data breach investigations report,” Accessed May. 01, 2022, 2021. [Online]. Avail- able: https://www.verizon.com/business/resources/reports/2021/ 2021-data-breach-investigations-report.pdf
10. O. Karajeh, D. Darweesh, O. Darwish, N. Abu-El-Rub, B. Als- inglawi, and N. Alsaedi, “A classifier to detect informational vs. non-informational heart attack tweets,” Future Internet, vol. 13, p. 19, 01 2021.
11. S. Malla and A. P.J.A., “COVID-19 outbreak: An ensemble pre-trained deep learning model for detecting informative tweets,” Applied Soft Computing, vol. 107, p. 107495, 2021. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S156849462100418X
12. S. Ohashi, T. Kajiwara, C. Chu, N. Takemura, Y. Nakashima, and H. Nagahara, “IDSOU at WNUT-2020 task 2: Identification of informative COVID-19 English tweets,” in Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020). Online: Association for Computational Linguistics, nov 2020, pp. 428–433. [Online]. Available: https://aclanthology. org/2020.wnut- 1.62
13. E. Kucuk, K. Yapar, D. Kucuk, and D. Kucuk, “Ontology-based automatic identification of public health-related Turkish tweets,” Computers in Biology and Medicine, vol. 83, 02 2017.
14. G. Raju, K. Subbaraj, and P. Kumaraguru, “Tweet-Scan-Post: A system for analysis of sensitive private data disclosure in online social media,” Knowledge and Information Systems, vol. 63, 09 2021.
15. Z. Yin, D. Fabbri, S. T. Rosenbloom, and B. A. Malin, “A scal- able framework to detect personal health mentions on Twitter,” Journal of Medical Internet Research, vol. 17, 2015.
16. R. Geetha, S. Karthika, N. Pavithra, and V. Preethi, “Tweedle: Sensitivity check in health-related social short texts based on regret theory,” Procedia Computer Science, vol. 165, pp. 663– 675, 2019, 2nd International Conference on Recent Trends in Advanced Computing ICRTAC -DISRUP - TIV INNOVATION , 2019 November 11-12, 2019. [Online]. Available: https:// www.sciencedirect.com/science/article/pii/S1877050920300703
17. A. Lamb, M. J. Paul, and M. Dredze, “Separating fact from fear: Tracking flu infections on Twitter,” pp. 789–795, jun 2013. [Online]. Available: https://aclanthology.org/N13-1097
18. P. Karisani and E. Agichtein, “Did you really just have a heart attack? Towards robust detection of personal health mentions in social media,” Proceedings of the 2018 World Wide Web Conference, 2018.
19. R. Saniei and V. Doncel, “PHDD: Corpus of physical health data disclosure on Twitter during COVID-19 pandemic,” SN Computer Science, vol. 3, 05 2022.
20. K. Jiang, S. Feng, Q. Song, R. Calix, M. Gupta, and G. Bernard, “Identifying tweets of personal health experience through word embedding and LSTM neural network,” BMC Bioinformatics, vol. 19, 06 2018.
21. W. B. Tesfay, J. Serna, and K. Rannenberg, “Privacybot: Detecting privacy sensitive information in unstructured texts,” in 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), 2019, pp. 53–60.
22. J. Lee, M. Decamp, M. Dredze, M. Chisolm, and Z. Berger, “What are health-related users tweeting? a qualitative content analysis of health-related users and their messages on Twitter,” Journal of Medical Internet Research, vol. 16, 10 2014.
23. W. Ahmed, R. Jagsi, T. Gutheil, and M. Katz, “Public disclosure on social media of identifiable patient information by health professionals: Content analysis of Twitter data,” Journal of Medical Internet Research, vol. 22, 09 2020.
24. J. Eichstaedt, R. Smith, R. Merchant, L. Ungar, P. Crutchley, D. Preotiuc-Pietro, D. Asch, and H. Schwartz, “Facebook lan- guage predicts depression in medical records,” Proceedings of the National Academy of Sciences, vol. 115, p. 201802331, 10 2018.
25. R. Thorstad and P. Wolff, “Predicting future mental illness from social media: A big-data approach,” Behavior Research Methods, pp. 1–15, 2019.
26. I. Syarif, N. Ningtias, and T. Badriyah, “Study on mental disorder detection via social media mining,” in 2019 4th In- ternational Conference on Computing, Communications and Security (ICCCS), 2019, pp. 1–6.
27. B. Alkouz, Z. A. Aghbari, and J. H. Abawajy, “Tweetluenza: Predicting flu trends from Twitter data,” Big Data Mining and Analytics, vol. 2, no. 4, pp. 273–287, 2019.
28. A. Khatua, A. Khatua, and E. Cambria, “A tale of two epi- demics: Contextual Word2vec for classifying Twitter streams during outbreaks,” Information Processing & Management, vol. 56, pp. 247–257, 01 2019.
29. H. Kucukali, O. Atac, A. S. Palteki, A. Z. Tokac, and O. Hayran, “Vaccine hesitancy and anti-vaccination attitudes during the start of COVID-19 vaccination program: A content analysis on Twitter data,” Vaccines, vol. 10, no. 2, 2022. [Online]. Available: https://www.mdpi.com/2076-393X/10/2/161
30. U. Tankut, M. Esen, and G. Balaban, “Analysis of tweets re- garding psychological disorders before and during the COVID- 19 pandemic: The case of Turkey,” Digital Scholarship in the Humanities, 12 2021.
31. J. Phua, S. Jin, and J. Kim, “Gratifications of using Face- book, Twitter, Instagram, or Snapchat to follow brands: The moderating effect of social comparison, trust, tie strength, and network homophily on brand identification, brand engagement, brand commitment, and membership intention,” Telematics and Informatics, vol. 34, 06 2016.
32. R. Vatrapu, R. R. Mukkamala, A. Hussain, and B. Flesch, “Social set analysis: A set theoretical approach to big data analytics,” IEEE Access, vol. 4, pp. 2542–2571, 2016.
33. M. Makita, A. Mas-Bleda, G. Morris, and M. Thelwall, “Mental health discourses on Twitter during mental health awareness week,” Issues in Mental Health Nursing, vol. 42, 09 2020.
34. “Kişisel Verilerin Korunması Kanunu,” Accessed May. 01, 2022. [Online]. Available: https://www.mevzuat.gov.tr/ mevzuatmetin/1.5.6698.pdf
35. L. Wissler, M. Almashraee, D. Monett, and A. Paschke, “The Gold Standard in corpus annotation,” 06 2014.
36. K. Tomanek, J. Wermter, and U. Hahn, “An approach to text corpus construction which cuts annotation costs and maintains reusability of annotated data,” 01 2007, pp. 486–495.
37. R. Snow, B. O’Connor, D. Jurafsky, and A. Y. Ng, “Cheap and fast—but is it good? Evaluating non-expert annotations for natural language tasks,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing, ser. EMNLP ’08. USA: Association for Computational Linguistics, 2008, p. 254–263.
38. S. Alqaraleh and M. Is ̧ık, “Efficient Turkish tweet classification system for crisis response,” Turkish Journal of Electrical Engineering & Computer Sciences, 11 2020.
39. A. A. Akın and M. D. Akın, “Zemberek-nlp,” Accessed May. 01, 2022. [Online]. Available: https://github.com/ahmetaa/zemberek- nlp
40. P. Bhardwaj, “Types of sampling in research,” Journal of the Practice of Cardiovascular Sciences, vol. 5, p. 157, 01 2019.
41. Scikit-learn machine learning in Python. Accessed May. 01, 2022. [Online]. Available: https://scikit-learn.org/stable/
42. R. Velioğlu, T. Yıldız, and S. Yıldırım, “Sentiment analysis using learning approaches over emojis for Turkish tweets,” in 2018 3rd International Conference on Computer Science and Engineering (UBMK), 2018, pp. 303–307.
43. “Fasttext library for efficient text classification and representation learning,” Accessed May. 01, 2022. [Online]. Available: https://fasttext.cc/
44. Z. Wang and S. Ji, “Learning convolutional text representations for visual question answering,” 05 2017.
45. G. Nergız, Y. Safali, E. Avarog ̆lu, and S. Erdog ̆an, “Classification of Turkish news content by deep learning based LSTM using Fasttext model,” in 2019 International Artificial Intelligence and Data Processing Symposium (IDAP), 2019, pp. 1–6.
46. B. Kuyumcu, C. Aksakalli, and S. Delil, “An automated new approach in fast text classification (FastText): A case study for Turkish text classification without pre-processing,” in Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval, ser. NLPIR 2019. New York, NY, USA: Association for Computing Machinery, 2019, pp. 1–4. [Online]. Available: https://doi.org/10.1145/3342827.3342828
47. O. Celik and B. Koc, “Classification of Turkish news text by TF-IDF, Word2vec and Fasttext vector model methods,” Deu Muhendislik Fakultesi Fen ve Muhendislik, vol. 23, pp. 121– 127, 01 2021.
48. H. Yagiz Erdinc and A. Guran, “Semi-supervised Turkish text categorization with Word2vec, Doc2vec and Fasttext algo- rithms,” in 2019 27th Signal Processing and Communications Applications Conference (SIU), 2019, pp. 1–4.
49. A. Tommasel and D. Godoy, “Short-text learning in social media: a review,” The Knowledge Engineering Review, vol. 34, p. e7, 2019.
50. A. Onan and S. Korukoglu, “A review of literature on the use of machine learning methods for opinion mining,” Pamukkale Univ Muh Bilim Derg, vol. 22, no. 2, pp. 111– 122, 2016, doi: 10.5505/pajes.2015.90018. [Online]. Available: https://dx.doi.org/10.5505/pajes.2015.90018
51. S.Kaddoura,G.Chandrasekaran,D.Popescu,andJ.Duraisamy, “A systematic literature review on spam content detection and classification,” PeerJ Computer Science, vol. 8, p. e830, 01 2022.