| Project/Area Number |
25460801
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Hygiene and public health
|
|---|
| Research Institution | Tottori University |
|---|
Principal Investigator |
INOUE Masashi 鳥取大学, 総合メディア基盤センター, 教授 (00176439)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
OKAMOTO Mikizo 鳥取大学, 医学部, 講師 (40032205)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | インフルエンザ / 流行予測 / ビッグデータ / 感染症 / インターネット / SNS / Twitter / Webマイニング |
|---|
| Outline of Final Research Achievements |
Having forecasts for infectious diseases can help support risk management and effective intervention against the outbreak of disease. Recently, Internet data from, for example, Google Trends and Twitter have been highlighted as valuable for faster detection of disease morbidity. The possibility to forecast the future incidence of influenza was analyzed using time series analysis based on retrospective data from the Japanese infectious disease surveillance. And also we investigated whether Internet data are promising data sources for monitoring influenza incidence. Several models were evaluated to find a model yielding the most accurate prediction. A nearest neighbor method was regarded as the best-fir model for the prediction. A comparison between the weekly number of Twitter messages containing the term of influenza and the national surveillance data revealed a strong relationship between both. Twitter messages seemed to be a useful data source to survey the influenza epidemic.
|
