| Project/Area Number |
15K12465
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Chuo University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
MAEDA Akira 東京大学, 大学院総合文化研究科, 教授 (30317309)
|
|---|
| Research Collaborator |
KAZUMI Takuro サイバーエージェント, 技術本部秋葉原ラボ, R&Dエンジニア
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | センチメント分析 / ファイナンス / 不動産 / テキスト・マイニング / ビッグ・データ |
|---|
| Outline of Final Research Achievements |
This research aims to quantify “sentiment” that invisibly reflects the psychology of economic agents and the atmosphere of economic and business activities. More specifically, by employing recent advances in the literature of natural language processing, we quantify the sentiment along a one-dimensional semantic axis, from negative to positive feelings. We repeat such a procedure every day to develop several types of “sentiment indexes” that might reflect the Japanese economy. We finally create thirty-four years’ worth daily sentiment indexes from the Nikkei articles. We then conduct an empirical analysis to show how persistently and robustly sentiment indexes can help predict Japanese stock prices as well as real estate prices including J-REITs, house prices and rents.
|
