2009 Fiscal Year Final Research Report
A study of spam blog filtering method based on its quantitative analysis
| Project/Area Number |
20700127
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
TOMOHIRO Fukuhara The University of Tokyo, 人工物工学研究センター, 特任助教 (50436581)
|
|---|
| Project Period (FY) |
2008 – 2009
|
| Keywords | スパムフィルタリング |
|---|
| Research Abstract |
A study of spam blog (splog) filtering method is conducted. For designing an efficient splog filter, we first created a splog dataset in which 50 persons judged blogs whether splogs or not. We then created a prototype splog filtering system. The system provides a user personalized splog filter by using a machine learning method called support vector machine (SVM). As evaluation results, we obtained F-value 0.738 for splogs which is higher than the value 0.656 of the previous method.
|
-
-
-
-
-
-
-
-
-
-
-
[Presentation] An Empirical Study on Selective Sampling in Active Learning for splog Detection2009
Author(s)
Katayama, T., Utsuro, T., Sato, Y., Yoshinaka, T., Kawada, Y., Fukuhara, T.
Organizer
The 5th International Workshop on Adversarial information Retrieval on the Web
Place of Presentation
Madrid (Spain)
Year and Date
2009-04-21
-
