A Study of Detecting "bad mouth" Comments in Social Media based on Actual Usage of Language Expressions
| Project/Area Number |
15K20884
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Childhood science (childhood environment science)
Web informatics, Service informatics
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
INUI Takashi 筑波大学, システム情報系, 准教授 (60397031)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
|
|---|
| Keywords | 自然言語処理 / 有害情報 / ソーシャルメディア / 誹謗中傷 / 固有表現認識 / エンティティリンキング / 仮想教師事例 |
|---|
| Outline of Final Research Achievements |
In this research project, we conduct a detailed survey of language expressions of libelous acts that lead to "bullying" on social media, and developed an automatic detection method of slander act based on the survey results. The main research results are as follows: (1) Survey on actual usage of language expression targeting about 5,000 text data, revealed appearance trend of slander expression and victim / perpetrator expression. (2) SVM based detection model considering the above tendency was proposed and its effectiveness was shown. (3) Knowledge-based features greatly contribute to automatic acquisition of victim information.
|
Report
(4 results)
Research Products
(6 results)
