| Project/Area Number |
23650076
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | National Institute of Informatics |
|---|
Principal Investigator |
AIZAWA Akiko 国立情報学研究所, コンテンツ科学研究系, 教授 (90222447)
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2011: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 視線計測 / 読解行動 / テキスト理解 / 自然言語処理 / 言語インタフェース / 視線計測装置 / 視線計測誤差 / 行動予測 / 文書構造理解 / 文書構造解析 |
|---|
| Research Abstract |
This research investigated a method for modeling human text reading behavior using both the eye-movement and linguistic analysis of the target text. First, we proposed a method for compensating gaze position measurement errors using text-reading specific information such as a word-bounding boxes layout and human reading patterns. Next, we studied models to predict human reading actions. In our formulation, each word in a document was characterized by fixation duration time, a position in a document, and linguistic features such as POS tag. The proposed models were verified through experiments using an existing gaze-corpus or experiments with our own subjects
|
