Detecting Personal Health Data Disclosures in Turkish Social Data
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.004 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".