WEB SCRAPING OF DISEASE INFORMATION FROM SOCIAL MEDIA TWITTER
| Autor: | Muhammad Iqbal Habibie, Taufiq Widiaputra, Yulianingsani Yulianingsani |
|---|---|
| Rok vydání: | 2022 |
| Zdroj: | Jurnal Teknoinfo. 16:246 |
| ISSN: | 2615-224X 1693-0010 |
| DOI: | 10.33365/jti.v16i2.1871 |
| Popis: | Environmental degradation caused by land conversion, trash (both domestic and industrial), and natural catastrophes is all variables that contribute to the establishment of disease susceptibility. Experts throughout the world suggest “ONE HEALTH” as a strategy for dealing with the threat of zoonoses. The One Health concept is a worldwide strategy to expand interdisciplinary collaboration and communication in all aspects of health care for humans, animals, and the environment. To overcome this disease of zoonoses, we developed a system of information zoonoses and Emerging Infectious Disease (SIZE). In this system of SIZE, we gather the disease information from social media. The disease information was collected from Twitter are Demam Berdarah Dengue (DBD), malaria disease, Antraks Disease, Canine Madness (Anjing Gila), Bird Flu (flu burung), and Ebola Disease. Twitter is a social media platform that has become a constant resource developing for data collectors. To perform this task to get the data of disease information, related tweets and Twitter user details the data collection using web scraping. Data Collection from Twitter was carried out by applying web scraping technology using python language. The scraping experiment from twitter in this study has succeeded in retrieving disease information from 2015-2020 using an advanced tool for Twitter scrapping called Twint using the python script. As the results lately have been increased number of tweets of diseases from canine madness (anjing gila) 34477, followed by Malaria Disease (28046) and Demam Berdarah Dengue (DBD) 11950 in 2020. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|