2017 Fiscal Year Final Research Report
Early Detection of Buzzwords Based on Large-scale Social Media Analysis
| Project/Area Number |
26330351
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Web informatics, Service informatics
|
|---|
| Research Institution | Kyoto Sangyo University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
張 建偉 岩手大学, 理工学部, 准教授 (20635924)
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Keywords | Webマイニング / トレンド分析 / 流行語早期発見 |
|---|
| Outline of Final Research Achievements |
In this project, we tried to develop a method for early detection of“gradual buzzwords” by analyzing time-series data of blog entries. We utilized 141 million blog entries from 11 million blog websites. Then, we studied two methods for detecting gradual buzzwords. One is a method which evaluates bloggers' buzzword prediction ability by analyzing how early bloggers mentioned past buzzwords. Another is a method based on observing the process in which certain topics grow to become major buzzwords and determining the key indicators that are necessary for their early detection. Moreover, we studied how to utilize trends and buzzwords of the world and also trends of individual interests in order to improve the accuracy for recommender systems of Web advertisement, cooking recipe, cosmetics and the reviews.
|
| Free Research Field |
情報工学
|
